CN110310137B

CN110310137B - Advertisement putting method and device

Info

Publication number: CN110310137B
Application number: CN201810229521.2A
Authority: CN
Inventors: 陈东
Original assignee: 3600 Technology Group Co ltd
Current assignee: 3600 Technology Group Co ltd
Priority date: 2018-03-20
Filing date: 2018-03-20
Publication date: 2023-10-20
Anticipated expiration: 2038-03-20
Also published as: CN110310137A

Abstract

The embodiment of the invention provides an advertisement putting method and device, and the method specifically comprises the following steps: acquiring expected target parameters of the advertisement effect of the advertiser on the first advertisement data; acquiring a factor set meeting the conditions according to historical advertisement putting data and expected target parameters; taking the factor set as a limiting condition, selecting a flow smaller than a flow threshold value to deliver the first advertisement data, and obtaining delivery experimental data; and when the throwing effect does not reach the expected target parameter, the factor set is adjusted, and when the throwing effect reaches the expected target parameter, the first advertisement data is thrown in full quantity. According to the embodiment of the invention, the corresponding throwing factors can be searched in the historical advertisement throwing experimental data according to the expected target parameters of the advertiser, the setting efficiency of the advertisement throwing factors is improved, and the obtained factor set is adjusted, so that the advertisement throwing can rapidly reach the expected of the advertiser.

Description

Advertisement putting method and device

Technical Field

The invention relates to the technical field of information security, in particular to an advertisement putting method and an advertisement putting device.

Background

With the development of the internet, electronic commerce is also rapidly developed, and internet advertisements are also generated by sellers in the internet in order to popularize goods.

In the prior art, there is a general advertisement delivery mode in the internet, and an advertiser sets some targeted delivery conditions, such as which website, video, time point, etc. the advertisement is to be delivered. For example, an advertiser needs to deliver an advertisement for a shampoo, and the advertiser needs to set a plurality of targeting conditions to limit the delivery of the advertisement for the shampoo.

The inventors have found in the practice of the present invention that the prior art has the following disadvantages:

the advertiser does not know how to set the targeting condition to make the advertising effect the best.

Disclosure of Invention

The present invention has been made in view of the above-mentioned problems, and has as its object to provide an advertising method and an advertising apparatus which overcome or at least partially solve the above-mentioned problems.

According to one aspect of the present invention, there is provided an advertisement delivery method including:

acquiring expected target parameters of the advertisement effect of the advertiser on the first advertisement data;

acquiring a factor set meeting a first preset condition according to historical advertisement putting data and the expected target parameters; the factor set comprises at least one delivery factor for delivering the first advertisement data;

Taking the factor set as a limiting condition, selecting a flow smaller than a flow threshold value to deliver the first advertisement data, and obtaining delivery experimental data;

when the delivery effect corresponding to the delivery experimental data does not reach the expected target parameter, adjusting the factor set according to the delivery experimental data, and executing the step of taking the factor set as a limiting condition, selecting a flow smaller than a flow threshold to deliver the first advertisement data to obtain the delivery experimental data;

and when the throwing effect corresponding to the throwing experimental data reaches the expected target parameter, throwing the first advertisement data in full quantity.

Optionally, after the step of obtaining the desired target parameter of the impression of the advertiser on the first advertisement data, the method further includes:

and acquiring historical advertisement putting data with similarity between the attribute information of the advertiser and the attribute information of the first advertisement data being larger than a first threshold value.

Optionally, the step of obtaining historical advertisement delivery data having a similarity with the attribute information of the advertiser and the attribute information of the first advertisement data greater than a first threshold value includes:

Determining the industry to which the advertiser belongs according to the registration information of the advertiser;

and acquiring historical advertisement putting data with the attribute information similarity larger than a first threshold value from the historical advertisement putting data of the industry.

Optionally, the step of obtaining the factor set meeting the first preset condition according to the historical advertisement putting data and the expected target parameter includes:

and carrying out attribution analysis on the historical advertisement putting data to obtain a factor set with the influence degree reaching the expected target parameter being greater than a second threshold.

Optionally, the step of performing attribution analysis on the historical advertisement delivery data to obtain a set of factors having an influence degree greater than a second threshold value reaching the expected target parameter includes:

determining each piece of first historical advertisement putting data matched with the expected target parameter from the historical advertisement putting data;

and taking the intersection of the placement factors of each piece of first historical advertisement placement data to obtain a first factor set.

Optionally, after the step of obtaining the first factor set, the step of obtaining the intersection of the placement factors of each piece of the first historical advertisement placement data further includes:

Determining that the initial throwing effect is smaller than the historical advertisement throwing data of the expected target parameter, and after adding or deleting the first throwing factor, correspondingly throwing the second historical advertisement throwing data with the throwing effect larger than or equal to the expected target parameter;

adding the increased first cast factor to the first set of factors, and deleting the pruned first cast factor from the first set of factors.

determining that the initial throwing effect is larger than the historical advertisement throwing data of the expected target parameter, and after adding or deleting the second throwing factor, correspondingly throwing the third historical throwing advertisement data with the throwing effect smaller than or equal to the expected target parameter;

deleting the added second put factor from the first set of factors and adding the pruned second put factor to the first set of factors.

Optionally, the attribute information of the first advertisement data includes: at least one of product information corresponding to the first advertisement data, content information corresponding to the first advertisement data, label information corresponding to the first advertisement data, and a brief description of the first advertisement data.

Optionally, the step of adjusting the factor set according to the delivery experimental data includes:

and carrying out attribution analysis on the input experimental data obtained by multiple input, and obtaining a factor set with the influence degree reaching the expected target parameter being greater than a second threshold.

Optionally, the method further comprises:

and stopping adjusting the factor set when the charging generated by putting the flow smaller than the flow threshold reaches a preset upper limit.

Optionally, after stopping the step of adjusting the factor set when the charging generated by delivering the flow smaller than the flow threshold reaches a preset upper limit, the method further includes:

sending delivery result test data to an account of the advertiser; the put result test data comprises a factor set and put effects

And when receiving a new expected target parameter sent by an advertiser, entering a step of acquiring a factor set meeting a first preset condition according to historical advertisement putting data and the expected target parameter based on the new expected target parameter.

Optionally, when the delivery effect corresponding to the delivery experimental data reaches the desired target parameter, the step of delivering the first advertisement data in full amount includes:

When the throwing effect corresponding to the throwing experimental data reaches the expected target parameter, sending throwing result test data to the account of the advertiser;

and after receiving the authorized delivery of the advertiser, delivering the first advertisement data in full quantity.

According to still another aspect of the present invention, there is provided an advertisement putting apparatus including:

the expected target parameter acquisition module is used for acquiring expected target parameters of the advertisement effect of the advertiser on the first advertisement data;

the factor set acquisition module is used for acquiring a factor set meeting a first preset condition according to the historical advertisement putting data and the expected target parameter; the factor set comprises at least one delivery factor for delivering the first advertisement data;

the throwing experiment data obtaining module is used for taking the factor set as a limiting condition, selecting the flow smaller than the flow threshold value to throw the first advertisement data, and obtaining throwing experiment data;

the factor set adjusting module is used for adjusting the factor set according to the throwing experiment data when the throwing effect corresponding to the throwing experiment data does not reach the expected target parameter, and executing the step of throwing the first advertisement data by selecting the flow smaller than the flow threshold value by taking the factor set as a limiting condition to obtain throwing experiment data;

And the delivery module is used for delivering the first advertisement data in full quantity when the delivery effect corresponding to the delivery experimental data reaches the expected target parameter.

Optionally, the historical advertisement delivery data acquisition module includes:

an industry determining unit, configured to determine, according to registration information of the advertiser, an industry to which the advertiser belongs;

the historical advertisement delivery data acquisition unit is used for acquiring historical advertisement delivery data with the attribute information similarity larger than a first threshold value from the historical advertisement delivery data of the industry.

Optionally, the factor set acquisition module includes:

and the first attribution analysis unit is used for carrying out attribution analysis on the historical advertisement putting data and acquiring a factor set with the influence degree reaching the expected target parameter being larger than a second threshold value.

Optionally, the first attribution analysis unit includes:

a first determining subunit, configured to determine, from the historical advertisement delivery data, each piece of first historical advertisement delivery data that matches the expected target parameter;

the first factor set obtaining subunit is configured to obtain an intersection of the placement factors of each piece of first historical advertisement placement data, and obtain a first factor set.

Optionally, the first attribution analysis unit further includes:

a second determining subunit, configured to determine, from the historical advertisement delivery data with the initial delivery effect smaller than the expected target parameter, second historical delivery advertisement data with a corresponding delivery effect greater than or equal to the expected target parameter after adding or deleting the first delivery factor;

a first scaling subunit operable to add the added first put factor to the first set of factors and delete the pruned first put factor from the first set of factors.

Optionally, the first attribution analysis unit further includes:

a third determining subunit, configured to determine, from the historical advertisement delivery data with the initial delivery effect greater than the desired target parameter, third historical delivery advertisement data with a corresponding delivery effect less than or equal to the desired target parameter after adding or deleting the second delivery factor;

a second scaling subunit operable to delete said increased second put factor from said first set of factors and add said pruned second put factor to said first set of factors.

Optionally, the factor set adjustment module includes:

and the second attribution analysis unit is used for attributing analysis to the throwing experiment data obtained by throwing for a plurality of times, and obtaining a factor set with the influence degree reaching the expected target parameter being larger than a second threshold value.

Optionally, the apparatus further comprises:

and the stop adjustment module is used for stopping adjusting the factor set when the charging generated by the delivery of the flow smaller than the flow threshold reaches a preset upper limit.

Optionally, the apparatus further comprises:

the sending module is used for sending the throwing result test data to the account of the advertiser; the delivery result test data comprises a factor set and a delivery effect.

And the receiving module is used for entering the step of acquiring a factor set meeting a first preset condition according to the historical advertisement putting data and the expected target parameters based on the new expected target parameters when receiving the new expected target parameters sent by the advertiser.

Optionally, the delivery module includes:

a sending unit, configured to send, to an account of the advertiser, delivery result test data when a delivery effect corresponding to the delivery experimental data reaches the desired target parameter;

And the delivery unit delivers the first advertisement data in full quantity after receiving the authorized delivery of the advertiser.

According to yet another aspect of the present invention, there is provided a computer program comprising: computer readable code which, when run on a terminal, causes the terminal device to perform any one of the advertising methods.

According to a further aspect of the present invention, there is provided a computer readable medium having stored therein a computer program as described above.

According to the advertisement putting method and device, expected target parameters of the advertisement effect of an advertiser on first advertisement data are obtained, and a factor set meeting a first preset condition is obtained according to historical advertisement putting data and the expected target parameters. Taking the factor set as a limiting condition, selecting a flow smaller than a flow threshold value to deliver the first advertisement data, and obtaining delivery experimental data; when the delivery effect corresponding to the delivery experimental data does not reach the expected target parameter, adjusting the factor set according to the delivery experimental data, and executing the step of taking the factor set as a limiting condition, selecting a flow smaller than a flow threshold to deliver the first advertisement data to obtain the delivery experimental data; and when the throwing effect corresponding to the throwing experimental data reaches the expected target parameter, throwing the first advertisement data in full quantity. According to the embodiment of the invention, the factor set can be adjusted through two stages, wherein the expected target parameter in the first stage is the expected target parameter required by the advertiser who needs to put the advertisement currently, the initial factor set is determined firstly according to the historical putting data, then the second stage is entered, the small flow putting attempt is carried out, and the factor set is continuously optimized, so that the advertiser can set the putting factor of the directional putting without setting the expected target parameter, the user operation is facilitated, and the obtained factor set is more objective and accurate.

The foregoing description is only an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present invention more readily apparent.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the alternative embodiments. The drawings are only for purposes of illustrating alternative embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:

FIG. 1 shows a schematic flow diagram of the steps of a method of advertising in accordance with one embodiment of the invention;

FIG. 2 shows a schematic flow diagram of the steps of a method of advertising in accordance with one embodiment of the invention;

FIG. 3 illustrates a flowchart of steps for obtaining historical advertising data having a similarity to the advertiser's attribute information and the attribute information of the first advertising data greater than a first threshold, in accordance with one embodiment of the present invention;

FIG. 4 is a flowchart illustrating steps for attributing analysis to the historical advertising data to obtain a set of factors having a degree of impact greater than a second threshold on reaching the desired target parameter, according to an embodiment of the present application;

FIG. 5 illustrates a schematic diagram of an advertising device in accordance with one embodiment of the present application;

FIG. 6 shows a schematic of an advertising device in accordance with one embodiment of the application;

FIG. 7 shows a schematic diagram of a historical advertising data acquisition module according to one embodiment of the application;

FIG. 8 shows a schematic structure of a first attribution analysis unit according to an embodiment of the present application;

fig. 9 is a schematic diagram of a hardware structure of an advertisement delivery device according to an embodiment of the present application.

Detailed Description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

Example 1

Referring to FIG. 1, a method for advertising according to one embodiment of the invention may specifically include the steps of:

step 101, obtaining expected target parameters of the advertisement effect of the advertiser on the first advertisement data.

In the embodiment of the invention, the advertiser can set the expected throwing effect of the advertiser on the first advertisement data. Wherein the desired target parameters include: click rate, conversion rate, etc.

In the embodiment of the present invention, for example, the advertiser needs to put the first advertisement data of a shampoo on a website, and the conversion rate of the first advertisement data is expected to reach 5%. The advertiser may log into the advertising platform and set the desired targeting parameter to a conversion rate of 5% for the first advertisement data.

The value of the desired target parameter set by the advertiser may be set according to the needs or actual situations, and in the embodiment of the present invention, the value of the desired target parameter is not specifically limited.

102, acquiring a factor set meeting a first preset condition according to historical advertisement putting data and the expected target parameters; the set of factors includes at least one placement factor for placement of the first advertisement data.

In the embodiment of the invention, a large amount of historical advertisement putting data is recorded in a database, and the historical advertisement putting data is a recorded result of a later putting process after each advertisement data is put. Each piece of historical advertisement putting data has corresponding attribute information, for example, one piece of historical advertisement putting data has corresponding advertiser information, product information, advertisement content, advertisement labels and the like, and also has a putting factor in historical putting and a putting effect achieved after putting. Specifically, the number of times of putting advertisement data, the number of times of clicking after putting, the number of times of purchasing products after browsing, etc. can be recorded, the clicking rate can be the number of times of clicking/putting, and the conversion rate can be the number of times of purchasing/putting.

In an embodiment of the present invention, the put factor includes: advertisement presentation principles, and/or web page content, and/or advertisement locations, and/or advertisement sizes, and/or advertisement placement areas, and/or advertisement placement time periods, and/or advertisement placement objects, etc.; for example, the principle of advertisement presentation may be that the content of advertisement presentation is determined according to the content of the web page and the search history of the user, for example, the user searches a "menu" in a search engine, and then presents the advertisement of kitchen ware or restaurant to the user. The advertising display principle may also be used to provide advertisements with other principles, such as users, and embodiments of the present invention are not limited in this regard. Web page content refers to content of other parts of an advertisement presentation page, for example, web page is knowledge content, or content of a television video class, or content of a shopping class, etc., and the content of the web page will largely determine the advertisement delivery effect. The advertisement position can be the display position of the advertisement in the webpage, the webpage has a certain layout, the advertisement is displayed in different positions, and different advertisement effects can be achieved. For example, if an advertisement is displayed at the top of a page, the click-through rate of the advertisement will typically be lower, and if an advertisement is displayed in the middle-upper portion, the click-through rate will typically be better. The size of an advertisement refers to the area ratio of the advertisement to the screen, and the aspect ratio of the advertisement. The advertisement delivery area allows delivery nationwide, for example, or only delivers terminals where the IP address of the Shanghai region is located, for example. The advertisement delivery period may, for example, only allow 8:00-10:00 night delivery. Advertising objects such as: allowing delivery to a population of users having various properties, such as female users, users aged 20-30 years, etc.

In the embodiment of the present application, the first preset condition may be to find a factor set with the greatest influence, where the factor set is a set of one or more put factors. Specifically, when the desired target parameter is conversion rate or click rate of 5%, selecting historical advertisement delivery data meeting the desired target parameter from all the historical advertisement delivery data, wherein the conversion rate or click rate corresponding to the historical advertisement delivery data is greater than or equal to 5%, or the conversion rate or click rate is 5% ± a%, a is an error, and the range of the value of a can be set according to actual requirements, and takes a certain value smaller than 5 according to requirements. And then carrying out attribution analysis on the throwing factors of the part of historical advertisement throwing data to obtain a factor set with the largest influence. For example, a first advertisement is selected from the historical advertisement placement data, and the placement factor of the first advertisement is obtained as follows: the advertisement display principle is that the advertisement is displayed according to the search related words, the webpage content is shopping content, the advertisement position is the lower left corner position, the advertisement size is 1/10 of the webpage, the click rate of the first advertisement is 8%, and the throwing factor of the selected second advertisement is as follows: the advertisement display principle is that according to the search related words, the webpage content is the knowledge popularization content, the advertisement position is the lower left corner position, the advertisement size is 1/10 of the webpage, the click rate of the second advertisement is 4.5%, the webpage content can be considered as shopping content as a factor with larger influence, the shopping content can be taken as one of the factor sets, other factor sets with the largest influence can be obtained in the same way, and the combination of the factors is taken as the factor set with the largest influence. Only an example of obtaining a set of factors meeting the first preset condition is given here. Wherein, the advertisement data which is not matched with the expected target parameters may be used for comparison in the attribution analysis process, and the attribution analysis specific method is not limited by the embodiment of the application. In the embodiment of the present application, the factor set meeting the first preset condition may also be obtained by other manners, which is not limited in the embodiment of the present application.

And 103, taking the factor set as a limiting condition, and selecting the flow smaller than a flow threshold to deliver the first advertisement data to obtain the delivery experimental data.

In the embodiment of the present invention, after an initial factor set is determined in step 102, for example, the factor set includes a website, time, user group, region, etc. for targeted advertisement delivery after advertisement delivery, a flow smaller than a flow threshold may be selected from flows satisfying the factor set of each website to deliver the first advertisement data, and according to statistics of the small flow on a delivery result of the first advertisement data, a small flow experiment is completed to obtain delivery experimental data.

In the embodiment of the invention, the throwing experiment data refer to throwing effects obtained by the first advertisement data after the small flow experiment, namely parameters such as conversion rate or click rate.

In the embodiment of the invention, since the delivery effect corresponding to the historical advertisement delivery data subjected to attribution analysis may be different from the delivery effect of the first advertisement data, the expected target parameters of the user cannot be achieved, so that after the factor set is obtained, the factor set is used as a limiting condition to carry out experimental delivery on the first advertisement data, the situation that the expected advertisement effect of the user cannot be achieved after full delivery is avoided, and the requirement of an advertiser cannot be met.

And step 104, when the release effect corresponding to the release experiment data does not reach the expected target parameter, adjusting the factor set according to the release experiment data, and executing step 103.

In the embodiment of the invention, when the delivery effect after the small flow delivery does not reach the expected target parameter, step 103 can be executed after the factor set is adjusted, and the small flow delivery experiment is performed again. And circularly carrying out the small flow delivery experiment until the delivery effect after the factor set adjustment reaches the expected target parameter or the preset condition for stopping the small flow delivery experiment is reached.

In the embodiment of the present invention, for example, when the factor set is: the advertisement putting time is that the user pops up when opening the webpage, the popping-up position is the lower right corner of the webpage, the advertisement is popped up for women aged 18-28 years, and the advertisement is popped up in northwest regions. When the factor sets are set as the orientation conditions, the throwing effect after the small flow experiment does not reach the expected target parameters of the advertiser. A set of adjustment factors comprising: pruning the cast factor or changing the content of the cast factor. If the advertisement is deleted in the northwest region, it means that the advertisement is ejected in the national region, or the age range is set to 18-35 years, or the like. And then carrying out a small-flow throwing experiment until the throwing effect of the experiment reaches the expected target parameters of the advertiser, and completing the experiment.

In the embodiment of the application, the condition for stopping the small-flow delivery experiment can be set, for example, the upper limit of the small-flow advertisement delivery budget is reached, the small-flow delivery experiment is not performed any more, the step 105 can be directly entered, and of course, the final experimental result, for example, the delivery effect and the factor set can be returned to the advertiser, for example, the terminal of the advertiser is returned for display, and the advertiser waits for further processing. If it is determined that the process proceeds to step 105, for example, when an advertiser confirmation operation is received, step 105 is performed. And when the advertiser readjusts the desired targeting parameters, step 101 may be re-performed.

Wherein, can set up a small flow advertisement and put the budget upper limit for the small flow to put experiments at the advertiser, make things convenient for the advertiser to control budget. Then the cost of the small flow experiment is continuously calculated in the subsequent small flow experiment process, and when the calculated upper limit is reached, the small flow experiment is stopped. Of course, in practical application, the advertiser may not set the small-traffic advertisement delivery budget upper limit, and then the embodiment of the application uses the account balance of the advertiser account as the small-traffic advertisement delivery budget upper limit, so as to avoid excessive delivery of traffic.

And 105, when the throwing effect corresponding to the throwing experimental data reaches the expected target parameter, throwing the first advertisement data in full quantity.

In the embodiment of the invention, when the throwing effect corresponding to throwing experimental data reaches the expected target parameter, the adjusted factor set is taken as a limiting condition, and the first advertisement data is thrown in all the flows meeting the limiting condition, namely the limitation of small flow is released, and full-scale throwing is performed.

According to the advertisement putting method and device, expected target parameters of the advertisement effect of an advertiser on first advertisement data are obtained, and a factor set meeting a first preset condition is obtained according to historical advertisement putting data and the expected target parameters. Taking the factor set as a limiting condition, selecting a flow smaller than a flow threshold value to deliver the first advertisement data, and obtaining delivery experimental data; when the delivery effect corresponding to the delivery experimental data does not reach the expected target parameter, adjusting the factor set according to the delivery experimental data, and executing the step of taking the factor set as a limiting condition, selecting a flow smaller than a flow threshold to deliver the first advertisement data to obtain the delivery experimental data; and when the throwing effect corresponding to the throwing experimental data reaches the expected target parameter, throwing the first advertisement data in full quantity. According to the embodiment of the invention, the factor set can be adjusted through two stages, wherein the first stage is to firstly determine the initial factor set according to the historical delivery data with the expected target parameters required by the advertiser needing to deliver the advertisement, then enter the second stage, and carry out small-flow delivery attempt, so that the factor set is continuously optimized, the advertiser can not set the delivery factor of directional delivery, only needs to set the expected target parameters, the operation of a user is convenient, and the obtained factor set is more objective and accurate.

Example two

Referring to FIG. 2, a flowchart illustrating steps of a method for advertising according to one embodiment of the invention may include the steps of:

step 201, obtaining expected target parameters of the advertisement effect of the advertiser on the first advertisement data;

step 202, obtaining historical advertisement putting data with similarity of attribute information of the advertiser and attribute information of the first advertisement data being larger than a first threshold value.

In a real-time example of the present invention, the attribute information of the first advertisement data includes: at least one of product information corresponding to the first advertisement data, content information corresponding to the first advertisement data, label information corresponding to the first advertisement data, and a brief description of the first advertisement data. Wherein the product information, such as advertising, is a game, an item, a website, etc.; content information, such as advertisements, is a video segment or a page or a picture that can be linked, etc. The tagging information may be information for manually tagging the first advertisement data according to the first advertisement data.

In the embodiment of the present invention, the step of obtaining historical advertisement delivery data having a similarity with the attribute information of the advertiser and the attribute information of the first advertisement data greater than a first threshold value, as shown in fig. 3, may preferably include the following substeps:

And S11, determining the industry of the advertiser according to the registration information of the advertiser.

In the real-time example of the present invention, the attribute information of the advertiser may refer to industry information that the advertiser belongs to, such as e-commerce, electronics, daily necessities, and the like. In the embodiment of the invention, the industry information of the advertiser is acquired through the registration information of the advertiser.

And a substep S12, obtaining historical advertisement putting data with the similarity of attribute information with the first advertisement data being greater than a first threshold value from the historical advertisement putting data of the industry.

In the embodiment of the invention, firstly, the historical advertisement putting data of the same industry as the advertiser is selected from all the historical advertisement putting data, and if the advertiser is an electronic commerce industry, all the historical advertisement putting data of the electronic commerce industry is selected. When the attribute information of the first advertisement data is an advertisement put for a certain discount activity by the electronic commerce, the attribute information of the first advertisement data can be labeled as: e-commerce discounting activities; and selecting historical advertisement putting data with labels which are discounted activities of the electronic commerce from all the historical advertisement putting data put by the electronic commerce in the same industry.

In an embodiment of the present invention, the first threshold includes: tag name similarity value, product similarity value, content similarity value, and the like. The corresponding first threshold value may be selected according to the attribute information, to which the present invention is not limited.

In practical application, each piece of advertisement data has corresponding advertisers, and the historical advertisement putting data of the advertisers with the similarity larger than the threshold value can be screened out according to the similarity of the advertisers of the first advertisement data and the attribute information of the advertisers of the historical advertisement putting data.

And 203, performing attribution analysis on the historical advertisement putting data to acquire a factor set with the influence degree reaching the expected target parameter being greater than a second threshold.

In the embodiment of the application, attribution analysis is performed on the selected historical advertisement putting data by taking the expected target parameter as a standard, wherein attribution analysis refers to analysis of the putting factors set by the historical advertisement putting data, namely the putting effect corresponding to each piece of historical putting data, and the influence degree of the effect achieved by the obtained factor set after analysis on the expected target parameter is greater than a second threshold.

For example, when the set of factors is: the advertisement putting time is that the user pops up when opening the webpage, the popping position is the lower right corner of the webpage, the advertisement pops up for women with ages of 18-28 years old, and the advertisement pops up in northwest areas, so that the effect degree of the putting factor of popping up when the advertisement putting time is that the user opens the webpage is small. The "pop-up advertisement for women aged 18-28" factor of delivery has a greater impact on achieving the desired target parameters.

In an embodiment of the present invention, performing attribution analysis on the historical advertisement delivery data to obtain a set of factors having an influence degree greater than a second threshold value reaching the desired target parameter, as shown in fig. 4, preferably may include the following substeps:

and a substep S21, determining each piece of first historical advertisement putting data matched with the expected target parameter from the historical advertisement putting data.

In the embodiment of the invention, each piece of historical advertisement putting data has a corresponding putting effect. For example, when the desired target parameter set by the advertiser is a conversion rate of 5%, the impression effect is selected from similar historical advertisement impression data to be a piece of first historical advertisement impression data with a conversion rate of more than 5% or a conversion rate of 5% ± a%.

In the embodiment of the invention, the matching condition can be set according to the requirement or actual situation. The embodiments of the present invention are not limited in this regard.

S22, taking intersection sets of the placement factors of each piece of first historical advertisement placement data to obtain a first factor set; then sub-steps S23 or S25 are performed.

In the embodiment of the invention, 3 pieces of first historical advertisement putting data are selected as described above, namely, the putting factor of the first historical advertisement putting data A is: the advertisement putting time is that the user pops up when opening the webpage, the popping-up position is the lower right corner of the webpage, the advertisement is popped up for women aged 18-28 years, and the advertisement is popped up in northwest regions. The placement factor of the first historical advertisement placement data B is: the advertisement putting time is that the advertisement is popped up once every 30 minutes after the user opens the webpage, the popping up position is the left upper corner of the webpage, the advertisement is popped up for females with the age of 18-25 years, and the advertisement is popped up in all regions of the whole country. The placement factor of the second historical advertising placement data C is: the advertisement putting time is that the advertisement is popped up once an hour after the user opens the webpage, the popped up position is the middle position of the webpage, the advertisement is popped up for women with the age of 18-35 years, and the advertisement is popped up in northeast. Taking the intersection of the placement factors of the three pieces of historical advertisement placement data as a first factor set as follows: the advertisement putting time is pop-up when the user opens the webpage, and pop-up advertisement for women aged 18-25 years.

In the substep S23, it is determined that, in the historical advertisement delivery data with the initial delivery effect smaller than the expected target parameter, after the first delivery factor is added or subtracted, the second historical advertisement delivery data with the corresponding delivery effect greater than or equal to the expected target parameter is delivered.

In the embodiment of the invention, the initial release effect is the release effect of the history release advertisement data in the history release, such as the click rate or conversion rate of the history release advertisement data in the history release. The determined initial throwing effect of the historical throwing advertisement data is smaller than the expected target parameter, and the historical throwing advertisement data corresponds to a throwing factor set of the historical throwing advertisement data, and after the first throwing factor is added or deleted, the throwing effect of the historical throwing advertisement data after the throwing is carried out again is good and can reach the expected target parameter or can reach the error range of the expected target parameter. The added first delivery factor is proved to be a strong delivery factor that would make the delivery effect better, or the deleted first delivery factor is a delivery factor that has a weak influence on the delivery effect.

For example, the first set of factors for the second historical placement advertisement data is: the advertisement display principle is that the advertisement is displayed according to the search related words, the webpage content is knowledge popularization content, the advertisement position is the lower left corner position, the advertisement size is 1/10 of the webpage, and the click rate of the first advertisement is 4%. In the later delivery, the addition of the factors to the factor set adds shopping factors to the webpage content or deletes the webpage content to the knowledge popularization content, and the click rate is 6%, so that the webpage content can be considered to be the shopping content as the delivery factor with larger influence on the advertisement delivery effect, and the webpage content is the knowledge popularization content as the delivery factor with weaker influence on the advertisement delivery effect.

Substep S24 of adding said increased first cast factor to said first set of factors and deleting said pruned first cast factor from said first set of factors

In the embodiment of the present invention, since the throwing effect can be improved after the first throwing factor is added or deleted, the first throwing factor can be added or deleted in the first factor set.

In the substep S25, it is determined that, in the historical advertisement delivery data with the initial delivery effect greater than the desired target parameter, after the second delivery factor is added or subtracted, the corresponding delivery effect is less than or equal to the third historical advertisement delivery data with the desired target parameter.

In the embodiment of the invention, when the initial delivery effect of the third historical delivery advertisement data in the historical advertisement delivery data is larger than the expected target parameter, the delivery effect is reduced instead after the second delivery factor of the third historical delivery advertisement data is added or deleted, and the expected target parameter is reduced or the error range of the expected target parameter can be reached. The added second impression factor is a weak impression factor that worsens the impression of the advertisement, or the deleted second impression factor is a strong impression factor that improves the impression of the advertisement.

Substep S26, deleting the added second put factor from the first set of factors, and adding the pruned second put factor to the first set of factors.

In the embodiment of the invention, when the second putting factor is a weak factor which can make the advertisement putting effect poor, the second putting factor is deleted from the first factor set, and when the second putting factor is a strong factor which can make the advertisement putting effect good, the second putting factor is added into the first factor set.

204, taking the factor set as a limiting condition, selecting a flow smaller than a flow threshold value to deliver the first advertisement data, and obtaining delivery experimental data;

step 205, when the delivery effect corresponding to the delivery experimental data does not reach the expected target parameter, adjusting the factor set according to the delivery experimental data, and executing the step of taking the factor set as a limiting condition, selecting a flow smaller than a flow threshold to deliver the first advertisement data, thereby obtaining the delivery experimental data;

the step 205 includes: and carrying out attribution analysis on the input experimental data obtained by multiple input, and obtaining a factor set with the influence degree reaching the expected target parameter being greater than a second threshold.

In the embodiment of the invention, with reference to the above manner, the effect of the first advertisement data put under the limitation of different factor sets is subjected to attribution analysis for multiple times, and the obtained final factor set can enable the effect of the first advertisement data put to be larger than the expected target parameter.

And 206, stopping adjusting the factor set when the charging generated by putting the flow smaller than the flow threshold reaches a preset upper limit.

In the embodiment of the invention, when the flow which is smaller than the flow threshold value is tested, the advertisement is put in actually, and certain flow resources are occupied, so that certain cost is generated in each test, and when the generated cost reaches the preset upper limit of an advertiser, the adjustment of the set of factors can be stopped.

Meanwhile, in the embodiment of the invention, budgets corresponding to different expected target parameters of advertisements are also different, if the expected target parameters which the advertiser needs to finally reach are higher, the budgets corresponding to higher, and if the expected target parameters which the advertiser needs to finally reach are lower, the budgets corresponding to lower.

In the embodiment of the invention, if the advertisement platform can give a limit, if the finally achieved advertisement putting effect is the click rate A ten thousand, the corresponding advertisement expense is a ten thousand, and if the putting effect is the click rate B ten thousand, the corresponding advertisement expense is B ten thousand. The advertiser may set the corresponding desired targeting parameters based on its own budget.

Step 207, sending the delivery result test data to the account of the advertiser; the delivery result test data comprises a factor set and a delivery effect.

In the embodiment of the invention, the factor set and the throwing effect are returned to the advertiser, so that the advertiser confirms whether the factor set is the targeting condition which the advertiser wants to throw, and confirms whether the throwing effect achieved by the advertiser is satisfied.

Step 208, when receiving a new expected target parameter sent by an advertiser, based on the new expected target parameter, a step of obtaining a factor set meeting a first preset condition according to historical advertisement delivery data and the expected target parameter is entered.

In the embodiment of the invention, when the expected target parameter set by the advertiser is too high, the expected target parameter of the advertiser still cannot be reached after a plurality of tests, the advertiser can reset reasonable expected target parameters according to the returned delivery effect, and a conforming factor set can be obtained according to the new expected target parameter.

And step 209, when the delivery effect corresponding to the delivery experimental data reaches the expected target parameter, sending delivery result test data to the account of the advertiser.

In the embodiment of the invention, after the delivery effect of the small-flow experimental data reaches the expectations of advertisers, the delivery result test data is sent to the advertisers. The delivery result test data comprises a factor set and a delivery effect. The advertiser is informed about the advertisement delivery mode and the delivery effect achieved after the advertisement uses the factors.

And 210, after receiving the authorized delivery of the advertiser, delivering the first advertisement data in full quantity.

In the embodiment of the invention, if the advertiser authorizes the advertisement to be put by using the factor set, the first advertisement data can be put in full quantity.

Example III

Referring to FIG. 5, a block diagram illustrating an advertisement delivery device according to one embodiment of the present invention may include the following modules:

a desired target parameter obtaining module 301, configured to obtain a desired target parameter of a impression of an advertiser on the first advertisement data;

the factor set obtaining module 302 is configured to obtain a factor set that meets a first preset condition according to historical advertisement delivery data and the expected target parameter; the factor set comprises at least one delivery factor for delivering the first advertisement data;

the putting experimental data obtaining module 303 is configured to select a flow smaller than a flow threshold to put the first advertisement data by using the factor set as a limiting condition, so as to obtain putting experimental data;

a factor set adjustment module 304, configured to adjust the factor set according to the placement experiment data when the placement effect corresponding to the placement experiment data does not reach the desired target parameter, and execute the step of taking the factor set as a limiting condition, selecting a flow smaller than a flow threshold to place the first advertisement data, and obtaining placement experiment data;

And the delivery module 305 is configured to deliver the first advertisement data in full when the delivery effect corresponding to the delivery experimental data reaches the desired target parameter.

As described with reference to fig. 6, on the basis of fig. 5, optionally, the apparatus further includes:

a historical advertisement delivery data obtaining module 306, configured to obtain historical advertisement delivery data having a similarity with the attribute information of the advertiser and the attribute information of the first advertisement data greater than a first threshold.

And the stop adjustment module 307 is configured to stop adjusting the factor set when the charging generated by delivering the flow smaller than the flow threshold reaches a preset upper limit.

A sending module 308, configured to send delivery result test data to an account of the advertiser; the delivery result test data comprises a factor set and a delivery effect.

The receiving module 309 is configured to, when receiving a new expected target parameter sent by an advertiser, enter a step of obtaining a factor set meeting a first preset condition according to historical advertisement delivery data and the expected target parameter based on the new expected target parameter.

The factor set acquisition module 302 includes:

A first attribution analysis unit 3021, configured to perform attribution analysis on the historical advertisement delivery data, and obtain a factor set that reaches the desired target parameter and has an influence degree greater than a second threshold.

The delivery module 305 includes:

a sending unit 3051, configured to send, when the delivery effect corresponding to the delivery experimental data reaches the desired target parameter, delivery result test data to the account of the advertiser;

and the putting unit 3052 is used for putting the first advertisement data in full quantity after receiving the authorized putting of the advertiser.

Optionally, referring to fig. 7, the historical advertisement delivery data obtaining module 306 includes:

an industry determining unit 3061, configured to determine, according to registration information of the advertiser, an industry to which the advertiser belongs;

the historical advertisement delivery data obtaining unit 3062 is configured to obtain, from the historical advertisement delivery data of the industry, historical advertisement delivery data having a similarity with the attribute information of the first advertisement data greater than a first threshold value.

Alternatively, referring to fig. 8, the first attribution analysis unit 3021 includes:

a first determining subunit 30211, configured to determine, from the historical advertisement delivery data, each piece of first historical advertisement delivery data that matches the desired target parameter;

A first factor set obtaining subunit 30212, configured to obtain a first factor set by taking an intersection of placement factors of each piece of first historical advertisement placement data.

A second determining subunit 30213, configured to determine, from the historical advertisement delivery data with the initial delivery effect less than the desired target parameter, second historical advertisement delivery data with the corresponding delivery effect greater than or equal to the desired target parameter after adding or deleting the first delivery factor;

a first scaling subunit 30214 configured to add the added first put factor to the first factor set and delete the pruned first put factor from the first factor set.

A third determining subunit 30215, configured to determine, from among the historical advertisement delivery data with initial delivery effects greater than the desired target parameter, third historical delivery advertisement data with corresponding delivery effects less than or equal to the desired target parameter after adding or deleting the second delivery factor;

a second scaling subunit 30216 configured to delete the added second put factor from the first factor set and add the pruned second put factor to the first factor set.

The factor set adjustment module 304 includes:

Desired targeting parameters fig. 9 is a schematic diagram of a hardware structure of an advertisement delivery device according to an embodiment of the present application. Fig. 9 is a specific embodiment of the implementation of fig. 5-8. As shown in fig. 9, the advertisement delivery device of the present embodiment includes a processor 91 and a memory 92.

The processor 91 executes computer program codes stored in the memory 92 to implement the information processing method of the advertisement putting apparatus of fig. 1 to 4 in the above-described embodiment.

The memory 92 is configured to store various types of data to support operation at the advertising device. Examples of such data include instructions, such as messages, pictures, videos, etc., for any application or method operating on the advertising device. The memory 92 may include a random access memory (random access memory, simply referred to as RAM) and may also include a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory.

Optionally, a processor 91 is provided in the processing assembly 90. The advertisement delivery device may further include: a communication component 93, a power supply component 94, a multimedia component 95, an audio component 96, an input/output interface 97 and/or a sensor component 98. The components and the like specifically included in the advertisement delivery device are set according to actual requirements, which are not limited in this embodiment.

The processing component 90 generally controls the overall operation of the advertising device. The processing assembly 90 may include one or more processors 91 to execute instructions to perform all or part of the steps of the methods of fig. 1-4 described above. Further, the processing component 90 may include one or more modules that facilitate interactions between the processing component 90 and other components. For example, the processing component 90 may include a multimedia module to facilitate interaction between the multimedia component 95 and the processing component 90.

The power supply assembly 94 provides power to the various components of the advertising device. The power components 94 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the advertising devices.

The multimedia component 95 includes a display screen that provides an output interface between the advertising device and the user. In some embodiments, the display screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the display screen includes a touch panel, the display screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation.

The audio component 96 is configured to output and/or input audio signals. For example, the audio component 96 includes a Microphone (MIC) configured to receive external audio signals when the advertising device is in an operational mode, such as a voice recognition mode. The received audio signals may be further stored in the memory 92 or transmitted via the communication component 93. In some embodiments, audio assembly 96 further includes a speaker for outputting audio signals.

Input/output interface 97 provides an interface between processing assembly 90 and peripheral interface modules, which may be click wheels, buttons, etc. These buttons may include, but are not limited to: volume button, start button and lock button.

Sensor assembly 98 includes one or more sensors for providing status assessment of various aspects of the advertising device. For example, sensor assembly 98 may detect the on/off status of the advertising device, the relative positioning of the assembly, the presence or absence of user contact with the advertising device. Sensor assembly 98 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact, including detecting the distance between the user and the advertising device. In some embodiments, the sensor assembly 98 may also include a camera or the like.

Communication component 93 is configured to facilitate communication between the advertising device and other devices, either wired or wireless. The advertising device may access a wireless network based on a communication standard, such as WiFi,2G, or 3G, or a combination thereof. In one embodiment, the advertisement delivery device may include a SIM card slot therein for inserting a SIM card, so that the advertisement delivery device may log onto a GPRS network to establish communication with a server via the internet.

From the above, the communication component 93, the audio component 96, the input/output interface 97, and the sensor component 98 in the embodiment of fig. 9 can be implemented as the input devices in the embodiments of fig. 5 to 8.

In an advertisement delivery device of this embodiment, the processor obtains user behavior information; determining a scene corresponding to the user behavior information by using a preset scene prediction model; and selecting advertisement data of at least one brand information from the plurality of brand information for putting according to the corresponding relation between the scene and the plurality of brand information.

Of course, the processor may also perform the methods of the other steps described above.

For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.

In summary, according to the advertisement putting device provided by the embodiment of the invention, the scene corresponding to the user behavior information is accurately determined according to the preset scene prediction model, the advertisement data of at least one brand information is selected from the plurality of brand information to be put according to the corresponding relation between the scene and the plurality of brand information, the advertisement data of the brand information in the scene is provided for the user according to the user demand, the workload and the labor cost for the user to acquire the advertisement number of the brand information required in the scene are reduced, meanwhile, the advertisement data of the brand information has better correlation with the user demand, and the advertisement putting accuracy is improved.

The algorithms and displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, the present invention is not directed to any particular programming language. It will be appreciated that the teachings of the present invention described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the present invention.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

Various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functions of some or all of the components of the advertising method and apparatus according to embodiments of the invention may be implemented in practice using a microprocessor or digital signal processor (DSP, digital Signal Process). The present invention can also be implemented as an apparatus or device program (e.g., a computer program and a computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present invention may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet platform, provided on a carrier signal, or provided in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names.

The invention discloses an advertisement putting method which comprises the following steps:

A2, the method of A1, after the step of obtaining the desired target parameter of the impression of the advertiser on the first advertisement data, further comprises:

A3, the method of A2, the step of obtaining historical advertisement delivery data with similarity of the attribute information of the advertiser and the attribute information of the first advertisement data being greater than a first threshold value, includes:

A4, the method of A1, wherein the step of obtaining the factor set meeting the first preset condition according to the historical advertisement putting data and the expected target parameter comprises the following steps:

A5, the method of A4, wherein the step of performing attribution analysis on the historical advertisement delivery data to obtain a factor set with the influence degree reaching the expected target parameter being greater than a second threshold value comprises the following steps:

A6, the method of A5, wherein after the step of obtaining the first factor set by taking the intersection of the placement factors of each piece of the first historical advertisement placement data, further comprises:

A7, the method of A5, wherein after the step of obtaining the first factor set by taking the intersection of the placement factors of each piece of the first historical advertisement placement data, further comprises:

The method of A8, wherein the attribute information of the first advertisement data includes: at least one of product information corresponding to the first advertisement data, content information corresponding to the first advertisement data, label information corresponding to the first advertisement data, and a brief description of the first advertisement data.

The method of A9, A1, wherein the step of adjusting the set of factors according to the dosing experimental data comprises:

A10, the method of A1, further comprising:

A11, the method of A10, after stopping the step of adjusting the factor set when the charging generated by delivering the flow smaller than the flow threshold reaches a preset upper limit, further comprises: :

sending delivery result test data to an account of the advertiser; the delivery result test data comprises a factor set and a delivery effect.

A12, the method of A1, when the delivery effect corresponding to the delivery experimental data reaches the expected target parameter, the step of delivering the first advertisement data in full quantity includes:

The invention discloses a B11, an advertisement putting device, comprising:

B12, the apparatus of B11, further comprising:

and the historical advertisement putting data acquisition module is used for acquiring historical advertisement putting data with the similarity of the attribute information of the advertiser and the attribute information of the first advertisement data being larger than a first threshold value.

B13, the device of B12, the historical advertisement delivery data acquisition module comprises:

B14, the apparatus of B11, the factor set acquisition module comprising:

B15, the apparatus of B14, the first attribution analysis unit comprising:

B16, the apparatus of B15, the first attribution analysis unit further comprising:

B17, the apparatus of B15, the first attribution analysis unit further comprising:

B18, the apparatus of B12, the attribute information of the first advertisement data including: at least one of product information corresponding to the first advertisement data, content information corresponding to the first advertisement data, label information corresponding to the first advertisement data, and a brief description of the first advertisement data.

B19, the apparatus of B11, the factor set adjustment module comprising:

B20, the apparatus of B11, further comprising:

B21, the apparatus of B11, the apparatus further comprising:

B22, the device of B11, the delivery module comprising:

Claims

1. An advertising method comprising:

When the throwing effect corresponding to the throwing experimental data reaches the expected target parameter, throwing the first advertisement data in full;

the step of obtaining the factor set meeting the first preset condition according to the historical advertisement putting data and the expected target parameter comprises the following steps:

performing attribution analysis on the historical advertisement putting data to obtain a factor set with the influence degree reaching the expected target parameter being greater than a second threshold;

the step of performing attribution analysis on the historical advertisement putting data to obtain a factor set with the influence degree reaching the expected target parameter being greater than a second threshold value comprises the following steps:

2. The method of claim 1, wherein after the step of obtaining desired targeting parameters for the impression of the advertiser to the first advertisement data, further comprises:

3. The method of claim 2, wherein the step of obtaining historical advertising data having a similarity to the advertiser's attribute information and the attribute information of the first advertising data greater than a first threshold value comprises:

4. The method of claim 1, wherein the step of taking the intersection of the placement factors for each piece of first historical advertising placement data to obtain the first set of factors further comprises:

5. The method of claim 1, wherein the step of taking the intersection of the placement factors for each piece of first historical advertising placement data to obtain the first set of factors further comprises:

6. The method of claim 2, wherein the attribute information of the first advertisement data includes: at least one of product information corresponding to the first advertisement data, content information corresponding to the first advertisement data, label information corresponding to the first advertisement data, and a brief description of the first advertisement data.

7. The method of claim 1, wherein the step of adjusting the set of factors based on the delivery experimental data comprises:

8. The method as recited in claim 1, further comprising:

9. The method of claim 8, further comprising, after stopping the step of adjusting the set of factors when a charge generated by delivery of the flow less than the flow threshold reaches a preset upper calculated limit:

sending delivery result test data to an account of the advertiser; the delivery result test data comprises a factor set and a delivery effect;

10. The method according to claim 1, wherein the step of delivering the first advertisement data in full amount when the delivery effect corresponding to the delivery experimental data reaches the desired target parameter includes:

11. An advertising device, comprising:

the delivery module is used for delivering the first advertisement data in full quantity when the delivery effect corresponding to the delivery experimental data reaches the expected target parameter;

The factor set acquisition module includes:

the first attribution analysis unit is used for carrying out attribution analysis on the historical advertisement putting data and acquiring a factor set with the influence degree reaching the expected target parameter being greater than a second threshold;

the first attribution analysis unit includes:

12. The apparatus of claim 11, wherein the apparatus further comprises:

13. The apparatus of claim 12, wherein the historical advertising data acquisition module comprises:

14. The apparatus of claim 11, wherein the first attribution analysis unit further comprises:

15. The apparatus of claim 11, wherein the first attribution analysis unit further comprises:

16. The apparatus of claim 12, wherein the attribute information of the first advertisement data comprises: at least one of product information corresponding to the first advertisement data, content information corresponding to the first advertisement data, label information corresponding to the first advertisement data, and a brief description of the first advertisement data.

17. The apparatus of claim 11, wherein the factor set adjustment module comprises:

18. The apparatus of claim 11, wherein the apparatus further comprises:

19. The apparatus of claim 18, wherein the apparatus further comprises:

The sending module is used for sending the throwing result test data to the account of the advertiser; the delivery result test data comprises a factor set and a delivery effect;

20. The apparatus of claim 19, wherein the delivery module comprises:

21. A computer readable medium having stored thereon a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the advertisement delivery method of any of claims 1-10.