CN108256982A - A flow response method, device and equipment - Google Patents

Abstract

The invention discloses a kind of flow response methods, are related to field of computer technology.The method, including：After the flow received from advertisement transaction platform, the sampling selection flow from the flow；For the flow for selection of sampling, advertisement transaction platform is returned to the selection ad data generation response of target value data；For statistics in first time period, the response generated with the target value data competes whether successful number is less than first threshold in advertisement transaction platform；If less than first threshold, then the target value data are adjusted with the first preset rules, into the step of after the flow received from advertisement transaction platform, sampling selects flow from the flow；If it is larger than or equal to first threshold, then for the flow except the flow for selection of sampling, advertisement transaction platform is returned to the selection ad data generation response of target value data.Thus it achieves and adjusts target value data with good groundsly, improve the advantageous effect of success rate that the participation of target value data is bidded.

Description

A flow response method, device and equipment

technical field

The present invention relates to the field of computer technology, in particular to a flow response method, device and equipment.

Background technique

RTB (Real Time Bidding, real-time bidding) auction system is a bidding technology that uses third-party technology to evaluate and bid for each user's display behavior on millions of websites. Different from the frequency of mass purchases, real-time bidding avoids invalid audience arrival and makes purchases for meaningful users. Its core is DSP (Demand Site Platform, demand-side platform). For the media, RTB can bring more advertising sales, realize sales process automation and reduce various expenses. Moreover, with the rapid popularization of smartphones and the maturity of the mobile network environment, the RTB market will be further explored, and programmatic buying will become a major trend in the digital marketing era.

However, RTB is an opaque auction mechanism, that is, if one of the DSPs participating in the bidding succeeds in the bidding, the other DSPs that fail the bidding will not know the transaction price of the bidding. Then, if the DSPs that did not bid successfully want to bid again for the traffic of the same ad space, there is still no reference, which leads to higher bidding frequency and lower probability of successful bidding.

Contents of the invention

In view of the above problems, the present invention is proposed to provide a flow response method, a flow response device, and a corresponding flow response device that overcome the above problems or at least partially solve the above problems.

According to one aspect of the present invention, a traffic response method is provided, including:

After receiving traffic from an ad exchange, sampling traffic from said traffic;

For the traffic selected by sampling, select advertising data with target value data to generate a response and return it to the advertising exchange platform;

Counting whether the number of times the responses generated with the target value data successfully compete in the advertising exchange platform within the first period of time is less than the first threshold;

If it is less than the first threshold, adjust the target value data according to the first preset rule, and enter the step of sampling and selecting traffic from the traffic received from the advertising trading platform;

If it is greater than or equal to the first threshold, for the flow other than the flow selected by sampling, select the advertisement data with the target value data to generate a response and return it to the advertisement exchange platform.

Optionally, the step of adjusting the target value data according to a first preset rule includes:

According to the dichotomy rule, the last target value data is adjusted.

Optionally, before the step of selecting advertisement data with target value data for traffic other than the traffic selected by sampling, generating a response and returning it to the advertising exchange platform, the method further includes:

Count whether the number of times the responses generated by the target value data successfully compete in the advertising exchange platform within the second time period is less than a second threshold; the second time period is greater than the first time period;

If it is less than the second threshold, adjust the target value data according to the first preset rule, and enter the step of sampling and selecting traffic from the traffic received from the advertising trading platform.

Optionally, before the step of selecting advertisement data with target value data for traffic other than the traffic selected by sampling, generating a response and returning it to the advertising exchange platform, the method further includes:

Statistics within the second time period, whether the number of times the responses generated by the target value data are successfully distributed in the advertising trading platform is evenly distributed; the second time period is greater than the first time period;

If the distribution is uneven, the target value data is adjusted according to a first preset rule, and the step of sampling and selecting traffic from the traffic received from the advertising trading platform is entered.

Optionally, the step of sampling and selecting traffic from the traffic after receiving the traffic from the advertising trading platform includes:

After receiving the traffic from the advertising trading platform, according to the dimension to which the traffic belongs, the traffic of the same dimension is sampled and selected.

Optionally, the step of selecting advertisement data with target value data for traffic other than the traffic selected by sampling and generating a response and returning it to the advertising exchange platform includes:

For the flow of the same dimension other than the flow selected by sampling, the target value data is used to select the advertisement data to generate a response and return it to the advertising exchange platform.

Optionally, after the step of selecting advertisement data with target value data for traffic other than the traffic selected by sampling, generating a response and returning it to the advertising exchange platform, the method further includes:

Judging whether the number of successful competitions of the responses generated with the target value data in the advertising exchange platform within any first time period following the generation of the target value data is less than the third threshold;

If it is not less than the third threshold, stop entering the traffic other than the traffic selected for sampling, select the advertising data with the target value data to generate a response and return to the advertising exchange platform, and reduce the target value data with the second preset rule, enter The step of selecting traffic by sampling from the traffic received from the advertising exchange platform.

Optionally, the dimension division parameters include at least one of advertisement position attributes, user attributes, and user interest dimensions.

According to another aspect of the present invention, a flow response device is provided, comprising:

A traffic sampling selection module, configured to sample and select traffic from the traffic received from the advertising trading platform;

The first response generation and return module is used for selecting the advertisement data with the target value data to generate a response and return it to the advertisement exchange platform for the traffic selected by the sampling;

The first counting module for the number of successful competitions is used to count whether the number of successful competitions in the advertising trading platform for the responses generated with the target value data within the first time period is less than the first threshold;

The first target value data adjustment module is used to adjust the target value data according to the first preset rule if it is less than the first threshold, and then enter the traffic sampling selection module;

The second response generating and returning module is configured to select advertisement data with target value data to generate a response to the advertising exchange platform for traffic other than the traffic selected by sampling if it is greater than or equal to the first threshold.

Optionally, the first target value data adjustment module includes:

The target value data adjustment sub-module is used to adjust the last target value data by dichotomy rule.

Optionally, before the second response is generated and returned to the module, it also includes:

The second statistical module for the number of successful competitions is used to count whether the number of successful competitions in the advertising exchange platform generated by the response generated with the target value data within the second time period is less than the second threshold; the second time period is greater than the second threshold A period of time; if it is less than the second threshold, enter the first target value data adjustment module.

Optionally, before the second response is generated and returned to the module, it also includes:

The competition success uniform judgment module is used to count whether the number of times of successful competition in the advertising trading platform for the responses generated by the target value data is evenly distributed within the second time period; the second time period is greater than the first time period; If the distribution is uneven, enter the first target value data adjustment module.

Optionally, the traffic sampling selection module includes:

The traffic sampling selection sub-module is also used to sample and select traffic from the traffic of the same dimension according to the dimension of the traffic received from the advertising trading platform.

Optionally, the second response generating and returning module is further configured to use target value data to select advertisement data and generate a response to the advertising exchange platform for traffic of the same dimension other than the traffic selected by sampling.

Optionally, after the second response is generated and returned to the module, it further includes:

The third statistical module for the number of successful competitions is used to judge whether the number of successful competitions in the advertising exchange platform for the response generated by the target value data is less than the third threshold;

The second target value data adjustment module is used to stop entering the traffic other than the traffic selected for sampling if it is not less than the third threshold, select the advertising data with the target value data to generate a response and return to the advertising exchange platform, and use the first The second preset rule reduces the target value data and enters the traffic sampling selection module.

Optionally, the dimension division parameters include at least one of advertisement position attributes, user attributes, and user interest dimensions.

According to another aspect of the present invention, a traffic response device is provided, including:

The memory is loaded with multiple executable instructions;

A processor that executes the plurality of executable instructions; the plurality of executable instructions includes a method for performing the following steps:

After receiving traffic from an ad exchange, sampling traffic from said traffic;

For the traffic selected by sampling, select advertising data with target value data to generate a response and return it to the advertising exchange platform;

Counting whether the number of times the responses generated with the target value data successfully compete in the advertising exchange platform within the first period of time is less than the first threshold;

If it is less than the first threshold, adjust the target value data according to the first preset rule, and enter the step of sampling and selecting traffic from the traffic received from the advertising trading platform;

If it is greater than or equal to the first threshold, for the flow other than the flow selected by sampling, select the advertisement data with the target value data to generate a response and return it to the advertisement exchange platform.

According to a flow response method of the present invention, after the flow received from the advertising exchange platform, the flow can be sampled and selected from the flow; for the flow selected by sampling, the target value data is used to select the advertising data to generate a response and return it to the advertising exchange platform; within the first period of time, whether the number of times the response generated by the target value data successfully competes in the advertising trading platform is less than the first threshold; if it is less than the first threshold, then the first preset rule is used to adjust the The target value data enters the step of sampling and selecting traffic from the traffic received from the advertising trading platform; if it is greater than or equal to the first threshold, then for the traffic other than the traffic selected by sampling, select with the target value data The advertisement data generates a response and returns it to the advertisement exchange platform. This solves the technical problem that in the existing traffic response method, the bidding success rate of each advertising account cannot be determined according to the target value data that meets the demand when bidding, resulting in a low bidding success rate. The beneficial effect of adjusting the target value data according to the basis and improving the success rate of the target value data participating in the bidding is obtained.

The above description is only an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention, it can be implemented according to the contents of the description, and in order to make the above and other purposes, features and advantages of the present invention more obvious and understandable , the specific embodiments of the present invention are enumerated below.

Description of 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 preferred embodiment. The drawings are only for the purpose of illustrating a preferred embodiment and are not to be considered as limiting the invention. Also throughout the drawings, the same reference numerals are used to designate the same components. In the attached picture:

FIG. 1 shows a flowchart of steps of a flow response method according to an embodiment of the present invention;

Fig. 1A shows a schematic diagram of an RTB process according to an embodiment of the present invention.

FIG. 2 shows a flowchart of steps of a traffic response method according to an embodiment of the present invention;

Fig. 3 shows a schematic structural diagram of a flow response device according to an embodiment of the present invention;

Fig. 4 shows a schematic structural diagram of a flow response device according to an embodiment of the present invention; and

Fig. 5 shows a schematic structural diagram of a traffic response device according to an embodiment of the present invention.

Detailed ways

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although 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 by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

Embodiment one

A traffic response method provided by an embodiment of the present invention is introduced in detail.

Referring to FIG. 1 , it shows a flowchart of steps of a flow response method in an embodiment of the present invention.

Step 110, after receiving the traffic from the advertising trading platform, select traffic from the traffic by sampling.

RTB is a bidding technology that uses third-party technology to evaluate and bid on each user's display behavior on millions of websites. FIG. 1A is a schematic diagram of an RTB process. The RTB process involves an advertising exchange (AdExchange, ADX) platform, a DSP, and a supply-side platform (Sell-Side Platform, SSP). Its core is the DSP platform. The DSP platform is like the headquarters of the display advertisement bidding: the first step is to send a request with user display information through its data tracking capability; the second step is to calculate the user display based on the estimation algorithm. value, and return the bid to the bid response engine; in the third step, the order is issued to the advertising trading system, and the advertising code is loaded to the major media, and finally delivered to the most accurate users.

Among them, the DSP platform allows advertisers and advertising agencies to access more easily and purchase advertising inventory more efficiently, because the platform brings together the inventory of various advertising exchanges. With this platform, there is no need for another cumbersome purchase step - a purchase request. SSPs enable publishers to also intervene in the ad exchange, making their inventory available. Through this platform, publishers hope to get the highest eCPM for their inventory without having to sell it at a low price. An open online advertising marketplace (similar to a stock exchange) that connects publishers and advertisers. The inventory of advertising space in the trading platform is not necessarily all premium inventory, as long as the publisher wants to provide it, it can be found there.

The following example illustrates the specific process of RTB:

Step 1, the user uses a browser to access a media website, such as website A. Website A presents the content of this website, such as news, to users. At the same time, media websites will also display advertisements to users on some advertising slots. Although the main job of media websites is to present high-quality content to users, they also need to make money through advertisements so that the business of providing content can continue. They can use their own sales force to sell advertising inventory. However, for media sites, RTB is an increasingly important channel for selling advertising inventory. Here we assume that website A decides to sell the advertising space in the upper right corner through RTB.

Step 2, website A transmits the information to the advertising trading platform. The transmitted information includes URL (UniformResource Locator, Uniform Resource Locator), advertisement location, user Cookie ID (Cookie Identity, Cookie identity code), etc.

In step 3, the advertising exchange platform organizes a bidding and sends traffic bidding responses to multiple DSPs. Assume advertiser 1 is one of the DSPs.

Step 4: When the DSP server corresponding to advertiser 1 receives the traffic bidding response from the advertising exchange platform, it transmits the data to the bidding engine.

Step 5: The bidding engine sends the user ID to the user and advertiser information database to see if the needs of the user and the advertiser match.

Step 6, the bidding engine receives the information of the user and the advertiser, and decides whether to participate in the bidding and the bidding price.

Step 7, the bidding engine generates a bidding response and transmits it to the DSP server. The bid response includes the bid price and other information such as which ad server to get the ad creative from.

Step 8: The DSP server corresponding to the advertiser 1 sends a bidding response to the advertising exchange platform.

In step 9, the advertising exchange platform conducts bidding after receiving responses from all DSP servers or when the deadline is reached. For example, the deadline of the advertising exchange platform is 100ms, which means that the time difference between the advertising exchange platform sending the traffic bidding response and receiving the DSP bidding response must be within the deadline. Assume that advertiser 1 is the winner of this advertising auction transaction.

In step 10, the advertising exchange platform notifies the user browser of the winner of the auction. The browser sends an advertisement exposure request to the advertisement server where the advertisement creative is located.

Step 11, the advertisement server sends the advertisement creative to the user's browser.

Step 12, the user sees an advertisement on the website. Then if the user is interested in the advertisement, he will click on the advertisement to enter the advertiser's landing page. Users browse the advertiser's website and may take further actions. For example, if the advertiser is an e-commerce company, the user may make a purchase on the e-commerce website.

As mentioned above, ADX will send a traffic request response, that is, a traffic bidding response to each advertiser in each DSP according to the received advertising space provided by the SSP, wherein the traffic request response includes the traffic in the embodiment of the present invention. Then, in the embodiment of the present invention, the traffic request response sent by the ADX can be obtained, and then the corresponding traffic can be obtained from the traffic request response. Of course, the traffic request response may not include traffic, but traffic-related information such as time, region, advertising space, and user corresponding to the traffic. Then at this time, traffic-related information can be obtained directly from the traffic request response, or the corresponding traffic can also be obtained according to the traffic request response, and so on. This embodiment of the present invention is not limited.

In practical applications, each website or media corresponding to the SSP can receive multiple user visits at the same time, and may generate a lot of traffic in a short period of time, then ADX can send traffic to each DSP at a higher frequency. Then, in order to detect the probability of successful bidding of the target value data of each advertising account participating in the bidding on each DSP side, if each traffic is judged, a lot of work will be wasted, and it is difficult to achieve real-time results. Therefore, in the embodiment of the present invention, after receiving the traffic from adx, the traffic can be sampled and selected from each traffic. The advertising account is the identity of the advertiser in the RTB system.

For example, according to the receiving time corresponding to the received traffic, one traffic can be sampled from the received traffic every preset time interval until the preset number of sampling traffic is reached; or other parameters can be selected from the received traffic. The flow is sampled and selected from the received flows; or the flow is randomly selected from the received flows; etc., which are not limited in this embodiment of the present invention. The preset time interval and the preset number of flows selected for sampling can be set according to requirements before this step, or before any step before this step, which is not limited in this embodiment of the present invention.

Moreover, in the embodiment of the present invention, specific rules for sampling and selecting traffic from the received traffic can be set before this step or any step before this step according to requirements, and this embodiment of the present invention does not Be limited.

Step 120, for the traffic selected by sampling, select advertisement data with target value data to generate a response and return it to the advertisement exchange platform.

For the traffic selected by sampling, the target value data can be used to select the advertisement data to generate a response and return it to adx. The specific process of selecting advertisement data for each sampling selected traffic is similar to selecting advertisement data for each traffic in the existing RTB system, and will not be repeated here. However, in the embodiment of the present invention, target value data can also be used as one of the criteria for selecting advertisement data. For example, the bidding price of each advertisement data can be obtained from the historically selected advertisement data of traffic A selected for a certain sample, and then the bid price B closest to the target value data can be obtained from each bid price, and the bidding price The advertisement data corresponding to the price B is returned to the corresponding ADX as the advertisement data generation response of the traffic A.

The target value data can be set before this step, or before any step before this step according to requirements, which is not limited in this embodiment of the present invention.

Step 130, counting whether the number of successful competitions in the advertising trading platform for the responses generated with the target value data within the first time period is less than a first threshold.

If the response generated with the target value data is successfully competed in adx, it means that the target value data at this time is the highest price offered by each advertising account participating in the corresponding traffic bidding. Then, in order to ensure the stability of target value data participating in successful bidding, you can set a first threshold and a first time period, and count whether the number of successful competitions in adx generated by target value data in the first time period is less than first threshold. And if the number of successful competitions in adx generated by the target value data is not less than the first threshold, it means that the target value data at this time participates in the bidding and the stability of success meets the requirements, so it is not necessary to adjust it at this time, but If the number of successful competitions in adx generated by the target value data is less than the first threshold, it means that the target value data at this time participates in the bidding and the success stability does not meet the requirements, then the target value data needs to be adjusted at this time , to make it more likely to bid successfully to meet the requirements. The first threshold and the first time period can be set before this step or any step before this step according to requirements, which is not limited in this embodiment of the present invention. Moreover, in the embodiment of the present invention, the value of the first threshold should not be greater than the number of flows selected for sampling.

For example, the first time period can be set to 5 minutes, and the current target value data is a yuan. If within 5 minutes from the current time to the current time, the number of responses to traffic generated with a yuan is 10 , where the number of successful competitions is 6. If the first threshold value is set to 6, then it can be determined that the number of times the response generated by the target value data a at this time successfully competes in adx is not less than the first threshold value; and if the first threshold value is set to 7, then it can be determined that At this time, the number of times the response generated by the target value data a successfully competes in adx is less than the first threshold.

Moreover, in the embodiment of the present invention, it is also possible to count whether the ratio of the number of successful competitions in adx to the number of responses generated by the target value data within the first time period is less than the second threshold; if it is less than the second Threshold, then adjust the target value data with the first preset rule, enter the step of sampling and selecting traffic from the traffic after receiving the traffic from adx; if it is greater than or equal to the second threshold, then select the traffic for sampling For traffic other than , use the target value data to select the advertisement data to generate a response and return it to adx. The second threshold must be a value less than or equal to 1. In the embodiment of the present invention, the specific value of the second threshold can also be set according to requirements before this step, or before any step before this step. , which is not limited in this embodiment of the present invention.

For example, the number of responses to the traffic generated with the target value data a is 10 times, and the number of successful competitions is 6. The responses generated with the current target value data a are the ones that compete successfully in adx The ratio of number of times to number of responses is 6/10, or 0.6.

In addition, in the embodiment of the present invention, in order to ensure the real-time performance, the flow may be sampled and selected from each flow continuously after the flow received from the adx. When counting whether the number of successful competitions in adx generated by the target value data is less than the first threshold, you can start from a certain moment and periodically count the responses generated by the current target value data in adx within the first time period Whether the number of successful competitions is less than the first threshold, until an input stop instruction is received, so as to stop continuing to perform statistics.

For example, assuming that the starting time is 8:00 on December 12, 2016, if minutes are used as the minimum timing unit, and the first time period is 5 minutes, then in the embodiment of the present invention, it can be set as December 2016 From 8:00 on December 12th to 8:00 on December 12th, 2016 is divided into the first first time period, and then for this first time period, count the goals corresponding to the current time period in this first time period Whether the number of successful competitions generated by value data in adx is less than the first threshold; divide the second first time period from 8:05 on December 12, 2016 to 8:10 on December 12, 2016, and then For the first time period, count whether the number of successful competitions in adx of the responses generated with the target value data corresponding to the current time period within the first time period is less than the first threshold; and execute in this cycle. You can also set the first time period from 8:00 on December 12, 2016 to 8:05 on December 12, 2016, and from 8:01 on December 12, 2016 to December 12, 2016. 8:06 on the 12th is divided into the second first time period, and so on. This embodiment of the present invention is not limited.

Furthermore, if the target value data is adjusted, it is necessary to start at a certain moment after the adjustment, and count the number of successful competitions in adx within the first period of time for responses generated with the current adjusted target value data Whether it is less than the first threshold.

Step 140, if it is greater than or equal to the first threshold, for traffic other than the traffic selected by sampling, select advertisement data with target value data to generate a response and return it to the advertisement exchange platform.

If within the first period of time, the number of successful competitions in adx generated by the target value data is greater than or equal to the first threshold, it means that the number of successful bids for the target value data meets the requirements, and at this time the target value data can be used as The bidding price of traffic other than the traffic selected by sampling, that is, for the traffic other than the traffic selected by sampling, the target value data can be used to select the advertisement data to generate a response and return it to adx.

Step 150, if it is less than the first threshold, then adjust the target value data according to the first preset rule, and then go to step 110.

And if within the first period of time, the number of successful competitions in adx generated by the target value data is less than the first threshold, it means that the number of successful bids for the target value data does not meet the requirements, and the target value needs to be adjusted at this time data so that it meets the needs. In the embodiment of the present invention, the target value data can be adjusted according to the first preset rule, and then continue to execute after receiving the traffic from adx, sample and select the traffic from each received traffic, and then make statistics within the first time period, Whether the number of successful competitions in adx for responses generated with adjusted target value data is less than the first threshold. In this embodiment of the present invention, the specific content of the first preset rule can be set before this step or any step before this step according to requirements, which is not limited in this embodiment of the present invention.

Specifically, the target value data can be increased according to a preset multiple, for example, the target value data can be adjusted to 1.5 times the original value each time, and then continue to sample and select traffic from each received traffic, and count in the first time period, Whether the number of successful competitions in adx generated by the adjusted target value data is less than the first threshold; the target value data can also be increased according to the preset increment, for example, increase the target value data by 1 yuan each time, and then continue from Sampling and selecting traffic from each received traffic, and counting whether the number of successful competitions in adx generated by the adjusted target value data within the first period of time is less than the first threshold; or according to other preset function forms Increase the target value data according to the ratio, for example, adjust the target value data to 1.5 times the original value and increase by 1 yuan each time, and then continue to sample and select traffic from each received traffic, and make statistics in the first time period to adjust Whether the number of successful competitions in adx of the responses generated by the last target value data is less than the first threshold; and so on. This embodiment of the present invention is not limited.

The aforementioned preset multiples and preset increments can be set before or before this step according to requirements, which is not limited in this embodiment of the present invention. Moreover, in this embodiment of the present invention, the specific content of the first preset rule may also be set before or before this step according to requirements, which is not limited in this embodiment of the present invention.

In the embodiment of the present invention, after the traffic received from adx, the traffic can be sampled and selected from the traffic; for the traffic selected by sampling, the advertisement data generation response is selected with the target value data and returned to adx; the statistics are at the first time In the section, whether the number of successful competitions in adx generated by the target value data is less than the first threshold; if it is less than the first threshold, then adjust the target value data with the first preset rule, and enter the received from adx After receiving the traffic, the step of sampling and selecting traffic from the traffic; if it is greater than or equal to the first threshold, then for the traffic other than the traffic selected by sampling, select advertisement data with target value data to generate a response and return to adx. Thus, the beneficial effect of adjusting the target value data according to the basis and improving the success rate of the target value data participating in the bidding is obtained.

Embodiment two

A traffic response method provided by an embodiment of the present invention is introduced in detail.

Referring to FIG. 2 , it shows a flowchart of steps of a flow response method in an embodiment of the present invention.

Step 210, after receiving the traffic from the advertising trading platform, select traffic from the traffic by sampling.

Optionally, in the embodiment of the present invention, the step 210 may further include:

Sub-step 211, after receiving the traffic from the advertising trading platform, according to the dimension of the traffic, select the traffic from the traffic of the same dimension by sampling.

In the embodiment of the present invention, according to the dimension to which each traffic received from adx belongs, the traffic belonging to the same dimension may be sampled and selected. For example, you can pre-set a fixed preset sampling ratio, and then extract selected traffic from each latitude according to the preset sampling ratio; you can also pre-set the number of personalized samples for different latitudes, and then follow the personalized sampling corresponding to each latitude The selected traffic is extracted from the corresponding latitude; or a fixed preset sampling number can be set for each latitude in advance, and then the selected traffic is extracted from the corresponding latitude according to the preset sampling number in each latitude; and so on. This embodiment of the present invention is not limited. For the above-mentioned preset sampling ratio, personalized sampling number and preset sampling number, all can be set before this step according to requirements, or before any step before this step, and this embodiment of the present invention does not Be limited.

The traffic latitude can be divided according to the traffic attributes. The traffic attributes can include the time corresponding to the traffic, the region corresponding to the traffic, the media context corresponding to the traffic, the size of the advertising space corresponding to the traffic, and the user information corresponding to the traffic. User information may include user attributes, user interest dimensions, user browsing records, and so on. Wherein, the time corresponding to the traffic refers to the corresponding generation time of the traffic, that is, the time when the user browses the webpage where the advertisement slot corresponding to the traffic is located. The region corresponding to the traffic refers to the region where the user is located when the user browses the webpage where the advertisement space corresponding to the traffic is located, and may include the IP (Internet Protocol, Internet Protocol) address of the user browsing the webpage. The media context corresponding to the traffic may include the context content of the webpage where the advertisement slot corresponding to the traffic is located. User attributes may include user's gender, age and other personal information. The user's interest dimension refers to the user's points of interest, which may include hobbies, social circles, and so on. In the embodiment of the present invention, the specific content of the traffic attributes to be extracted can be set according to requirements before this step, or in any step before this step, which is not limited in this embodiment of the present invention.

Optionally, in the embodiment of the present invention, the dimension division parameters include at least one of advertisement slot attributes, user attributes, and user interest dimensions.

Among them, the attributes of the advertisement may include the size of the advertising space, the context corresponding to the advertising space, etc.; the attributes of the user may include the user ID, user gender, user age, user location, user access time, etc.; the user's interest dimension may include the user's Consumption records, user hobbies, user historical access records, etc. This embodiment of the present invention is not limited.

In the embodiment of the present invention, the specific rules for dividing the latitude of the traffic according to the dimension division parameters can be set before this step or any step before this step according to requirements, which is not limited in this embodiment of the present invention. For example, it is possible to set the dimension division parameter so that all traffic belongs to the same latitude, and so on.

Step 220, for the traffic selected by sampling, select advertisement data with target value data to generate a response and return it to the advertisement exchange platform.

Step 230, counting whether the number of successful competitions in the advertising trading platform generated by the target value data within the first time period is less than the first threshold; if greater than or equal to the first threshold, enter step 240; if less than the first threshold A threshold, then go to step 290.

Step 240, counting whether the number of successful competitions in adx generated by the target value data within the second time period is less than a second threshold; the second time period is greater than the first time period; if it is less than the second threshold , then go to step 290, and then go to step 210.

In order to further determine the possibility of participating in the auction with target value data and succeeding, it is possible to further determine whether it is more accurate than the first time period before selecting advertising data with target value data to generate a response for traffic other than the traffic selected by sampling and returning it to adx. Whether the number of successful competitions in adx for responses generated with target value data within a long period of time is less than the second threshold. Therefore, in the embodiment of the present invention, it is counted whether the number of successful competitions in adx of the responses generated with the target value data within the second time period is less than the second threshold. The second time period is greater than the first time period. Then if within the second period of time, the number of successful competitions in adx generated with the current target value data is less than the second threshold, it means that the performance of participating in the bidding with the target value data and succeeding does not meet the requirements, then you need The target value data is adjusted, and in the embodiment of the present invention, the target value data can be adjusted according to a first preset rule. And if within the second period of time, the number of successful responses in adx generated with the current target value data is not less than the second threshold, then for traffic other than the traffic selected by sampling, the target value data can be used to select The advertisement data generation response is returned to adx. The second threshold may be set before this step or any step before this step according to requirements, which is not limited in this embodiment of the present invention.

In addition, in the embodiment of the present invention, it is also possible to count whether the ratio of the number of successful competitions in adx to the number of responses generated by the target value data within the second time period is less than the second preset ratio; The second time period is greater than the first time period; if it is less than the second preset ratio, go to step 290, and then go to step 210; and if it is not less than the second preset ratio, go to step 250. If step 250 does not exist, then go to step 260 directly. The second preset ratio can also be set before this step or any step before this step according to requirements, which is not limited in this embodiment of the present invention.

Of course, in order to further judge the stability of the bidding success of the target value data, if within the second period of time, the number of successful competitions in adx generated with the current target value data is not less than the second threshold, then further statistics can be made In the second time period, whether the distribution of the number of successful competitions in adx by the responses generated by the target value data is even.

Step 250, counting whether the distribution of the number of successful competitions in the advertising trading platform for the responses generated by the target value data within the second time period is uniform; the second time period is greater than the first time period; if the distribution is not uniform, Then go to step 290, and then go to step 210.

In the embodiment of the present invention, it is also possible to further count whether the distribution of the number of successful competitions in adx of the responses generated with the target value data within the second time period is even. The second time period is greater than the first time period.

Specifically, the second time period can be divided into multiple sub-time periods, and then the number of times the responses generated with the target value data in each sub-time period are successfully competed in adx is counted, and then the number of times corresponding to each sub-time period is compared Whether the difference between the times exceeds the preset maximum difference. If the difference between the times corresponding to each sub-time period exceeds the preset maximum difference, it can be determined that the response generated by the target value data is within the second time period. The number of successful competitions in adx is unevenly distributed; and if the difference between the number of times corresponding to each sub-time period does not exceed the preset maximum difference, it can be determined that in the second time period, the target value data is generated The responses of adx are evenly distributed in the number of successful competitions.

It is also possible to count the bidding time corresponding to the number of times the responses generated by the target value data successfully compete in adx within the second time period, and then compare the difference between the bidding times, if there are more than the preset number If the difference is less than the preset minimum difference, it can be determined that within the second time period, the number of times the responses generated with the target value data successfully compete in adx is unevenly distributed; and if there is no difference exceeding the preset number If the value is smaller than the preset minimum difference, it can be determined that the number of successful competitions in adx for the responses generated with the target value data is evenly distributed within the second time period.

In the embodiment of the present invention, the specific method of counting whether the distribution of times of successful competition in adx of the responses generated with the target value data within the second time period can be pre-set according to requirements is uniform, and this embodiment of the present invention does not add limited.

And if within the second time period, the number of successful competitions in adx of the responses generated with the target value data is evenly distributed, then step 260 can be entered, and if within the second time period, the responses generated with the target value data are within adx If the number of successful competitions is unevenly distributed, it is necessary to adjust the target value data, and at this time, it is necessary to enter step 290 .

In addition, in the embodiment of the present invention, both step 240 and step 250 can be performed before step 260 or any step before step 260, and step 240 can also be performed after step 250 or simultaneously with step 250, or Only one of step 240 and step 250 is executed, which is not limited in this embodiment of the present invention.

Step 260, for traffic other than the traffic selected by sampling, select advertisement data with target value data to generate a response and return it to the advertisement exchange platform.

Optionally, in the embodiment of the present invention, the step 260 may further include:

In sub-step 261, for traffic of the same dimension other than the traffic selected by sampling, select advertisement data with target value data to generate a response and return it to the advertisement exchange platform.

As mentioned above, if in the embodiment of the present invention, after each flow received from adx, according to the dimension to which each flow belongs, the flow is sampled and selected from the flow of the same dimension.

Then the target value data is also for the traffic selected by sampling in the same dimension. Therefore, if the target value data is determined to meet the demand, only the traffic of the same dimension other than the traffic selected by sampling can be used to select advertising data with the target value data. Generate a response back to adx. It is not possible to select advertising data with target value data to generate a response and return it to adx for traffic of other dimensions than the traffic selected by sampling.

Step 270 , judging whether the number of times the responses generated with the target value data successfully compete on the advertising exchange platform within any first time period following the generation of the target value data is less than a third threshold.

In practical applications, if the target value data is set relatively high, then the number of successful auctions with the target value data within a certain period of time must be relatively large, but this will lead to an increase in the bidding cost of the corresponding advertising account, and if In order to succeed in the bidding, other advertising accounts that failed to bid continuously increase their own bidding prices to be higher than the target value data, then they will also increase the transaction price of the traffic, making the price of the traffic falsely high, and further increasing the bidding cost of each advertising account.

Therefore, in the embodiment of the present invention, in order to avoid the above-mentioned problems caused by excessively high target value data, it is possible to determine the number of successful competitions in adx for responses generated with target value data within any first time period after the target value data generation response Whether it is less than to the third threshold. If within any first period of time after the response is generated with the target value data, the number of times the response generated with the target value data successfully competes in adx is less than the third threshold, it means that the target value data at this time is not inflated, Then you can continue to execute the step of selecting advertisement data with target value data to generate a response to return to adx for traffic other than the traffic selected by sampling; and if within any first period of time after generating a response with target value data, use target value The number of successful competitions generated by the data in adx is not less than the third threshold, which means that the target value data at this time may be falsely high. In order to avoid the above problems, it is necessary to stop entering traffic other than the traffic selected for sampling , the step of selecting advertisement data with target value data, generating a response and returning to adx. Make adjustments to the target value data. In the embodiment of the present invention, the target value data can be reduced by using the second preset rule.

In the embodiment of the present invention, the above-mentioned third threshold may be set according to requirements before this step, or before any step before this step, which is not limited in this embodiment of the present invention.

Step 280, if it is not less than the third threshold, stop entering the traffic other than the traffic selected for sampling, select the advertisement data with the target value data, generate a response and return to the advertising exchange platform, and reduce the target value with the second preset rule data, and then go to step 210.

As mentioned above, if within any first period of time after the response is generated with the target value data, the number of times the response generated with the target value data successfully competes in adx is not less than the third threshold, then stop entering the traffic selected for sampling For traffic other than , use the target value data to select the advertisement data to generate a response and return to the step of adx, and use the second preset rule to reduce the target value data.

Specifically, the second preset rule may be to adjust the target value data to a preset ratio of the original target value data, such as adjusting the target value data to one-half or one-third of the original, etc.; the second preset The rule can also be to adjust the target value data to the original target value data minus the preset reduction value, for example, to adjust the target value data to the original target value data minus 2 yuan; or to adjust the target value data to the original target value The difference between the preset ratio of the data and the preset reduction value, for example, adjust the target value data to the difference between one-half of the original target value data and 2 yuan, that is, target value data = original target value data * 1/ 2-2; or reduce the target value data according to the ratio of other functional forms, which is not limited in this embodiment of the present invention. In this embodiment of the present invention, the specific content of the second preset rule can be set according to requirements before this step, or before any step before this step, which is not limited in this embodiment of the present invention. The above preset ratio and preset reduction value can be set before this step or any step before this step according to requirements, which is not limited in this embodiment of the present invention.

Step 290, adjust the target value data according to the first preset rule, and go to step 210.

Optionally, in the embodiment of the present invention, the step 290 may further include:

Sub-step 291, adjust the last target value data by dichotomy rule.

In the embodiment of the present invention, the first preset rule may be a dichotomous rule, then when adjusting the target value data according to the first preset rule, the last target value data may be adjusted by using the dichotomous rule. The dichotomy rule includes that if the bidding fails, the target value data can be adjusted to twice the last target value data, and the adjusted target value data can continue to participate in the bidding. If the bidding still fails, the target value can be adjusted again. The value data is adjusted to twice the last target value data, and the adjusted target value data is used again to continue to participate in the bidding, and so on until the bidding is successful. Then, in the embodiment of the present invention, it can be set that if the statistics are within the first time period, the number of successful competitions in adx generated by the current target value data is less than the first threshold; or if the statistics are within the second time period, The number of times the response generated with the current target value data successfully competes in adx is less than the second threshold; or within the second time period, the response generated with the current target value data is unevenly distributed in the number of times the response is successfully competed in adx, then Then use the dichotomy rule to adjust the current target value data until the adjusted target value data does not meet the above conditions, then in the first time period, the response generated by the adjusted target value data competes in adx The number of successes is not less than the first threshold; or the number of successful competitions in adx for the responses generated with the adjusted target value data within the second time period is not less than the second threshold; or the statistics are in the second time period Within , responses generated with adjusted target value data had an even distribution of competitive successes in ADX.

In the embodiment of the present invention, after the traffic received from adx, the traffic can be sampled and selected from the traffic; for the traffic selected by sampling, the advertisement data generation response is selected with the target value data and returned to adx; the statistics are at the first time In the section, whether the number of successful competitions in adx generated by the target value data is less than the first threshold; if it is less than the first threshold, then adjust the target value data with the first preset rule, and enter the received from adx After receiving the traffic, the step of sampling and selecting traffic from the traffic; if it is greater than or equal to the first threshold, then for the traffic other than the traffic selected by sampling, select advertisement data with target value data to generate a response and return to adx. Thus, the beneficial effect of adjusting the target value data according to the basis and improving the success rate of the target value data participating in the bidding is obtained.

Moreover, in the embodiment of the present invention, before the traffic other than the traffic selected by sampling is selected with the target value data and the response is returned to adx, it is also possible to count the advertisement data with the target value data within the second time period Whether the number of successful competitions of the generated responses in adx is less than the second threshold; the second time period is greater than the first time period; at the same time, within the second time period, the responses generated with the target value data compete in adx Whether the number of successes is evenly distributed; and after the target value data is used to select the advertising data generation response and return it to adx for traffic other than the traffic selected by sampling, it can also be judged that the target value data generation response is followed by any first time In the segment, whether the number of successful competitions in adx generated by the target value data is less than the third threshold, so as to further improve the validity of the adjusted target value data.

For the method embodiment, for the sake of simple description, it is expressed as a series of action combinations, but those skilled in the art should know that the embodiment of the present invention is not limited by the described action order, because according to the embodiment of the present invention , certain steps may be performed in other order or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification belong to preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

Embodiment Three

A flow response device provided by an embodiment of the present invention is introduced in detail.

Referring to FIG. 3 , it shows a schematic structural diagram of a flow response device in an embodiment of the present invention.

The traffic sampling selection module 310 is configured to sample and select traffic from the traffic received from adx.

The first response generating and returning module 320 is configured to select advertisement data with target value data to generate a response to adx for the traffic selected by sampling.

The first competition success counting module 330 is used to count whether the number of successful competitions in adx of the response generated by the target value data within the first time period is less than the first threshold; if it is less than the first threshold, enter the first threshold A target value data adjustment module 350; if it is greater than or equal to the first threshold, enter the second response generation return module 340.

The second response generating and returning module 340 is configured to select advertisement data with target value data to generate a response to adx for traffic other than the traffic selected by sampling.

The first target value data adjustment module 350 is configured to adjust the target value data according to a first preset rule, and then enter the traffic sampling selection module.

In the embodiment of the present invention, after the traffic received from adx, the traffic can be sampled and selected from the traffic; for the traffic selected by sampling, the advertisement data generation response is selected with the target value data and returned to adx; the statistics are at the first time In the section, whether the number of successful competitions in adx generated by the target value data is less than the first threshold; if it is less than the first threshold, then adjust the target value data with the first preset rule, and enter the received from adx After receiving the traffic, the step of sampling and selecting traffic from the traffic; if it is greater than or equal to the first threshold, then for the traffic other than the traffic selected by sampling, select advertisement data with target value data to generate a response and return to adx. Thus, the beneficial effect of adjusting the target value data according to the basis and improving the success rate of the target value data participating in the bidding is obtained.

Embodiment Four

A flow response device provided by an embodiment of the present invention is introduced in detail.

Referring to FIG. 4 , it shows a schematic structural diagram of a flow response device in an embodiment of the present invention.

The traffic sampling selection module 410 is configured to sample and select traffic from the traffic received from adx.

Optionally, in the embodiment of the present invention, the traffic sampling selection module 410 further includes:

The traffic sampling selection sub-module is also used for sampling and selecting traffic from the traffic of the same dimension according to the dimension of the traffic after receiving the traffic from adx.

Optionally, in the embodiment of the present invention, the dimension division parameters include at least one of advertisement slot attributes, user attributes, and user interest dimensions.

The first response generating and returning module 420 is configured to select advertisement data with target value data and generate a response to adx for the traffic selected by sampling.

The first competition success counting module 430 is used to count whether the number of successful competitions in adx of the response generated by the target value data within the first time period is less than the first threshold; if it is less than the first threshold, enter the first threshold A target value data adjustment module 490; if it is greater than or equal to the first threshold, enter the second response generation return module 460.

The second competition success counting module 440 is used to count whether the number of successful competitions in adx of the response generated by the target value data is less than a second threshold within a second time period; the second time period is greater than the first Time period; if it is less than the second threshold, enter the first target value data adjustment module 490 .

The competition success uniform judgment module 450 is used to make statistics within the second period of time, whether the number of times of success of the competition in adx is evenly distributed with the response generated by the target value data; the second period of time is greater than the first period of time; if If the distribution is uneven, enter the first target value data adjustment module 490 .

The second response generating and returning module 460 is configured to select advertisement data with target value data and generate a response to adx for traffic other than the traffic selected by sampling.

Optionally, in the embodiment of the present invention, the second response generation and return module 460 is further configured to select advertisement data with target value data to generate a response to adx for traffic of the same dimension other than the traffic selected by sampling .

The third competition success counting module 470 is used to judge whether the number of successful competitions in adx of the response generated by the target value data is less than the third threshold within any first time period following the generation of the target value data response .

The second target value data adjustment module 480 is used for if it is not less than the third threshold, then stop entering the traffic other than the traffic selected for sampling, select the advertisement data generation response with the target value data to return to the step of adx, and use the second Preset rules reduce the target value data and enter the traffic sampling selection module 410 .

The first target value data adjustment module 490 is configured to adjust the target value data according to a first preset rule, and then enter the traffic sampling selection module 410 .

Optionally, in the embodiment of the present invention, the first target value data adjustment module 490 further includes:

The target value data adjustment sub-module is used to adjust the last target value data by dichotomy rule.

In the embodiment of the present invention, after the traffic received from adx, the traffic can be sampled and selected from the traffic; for the traffic selected by sampling, the advertisement data generation response is selected with the target value data and returned to adx; the statistics are at the first time In the section, whether the number of successful competitions in adx generated by the target value data is less than the first threshold; if it is less than the first threshold, then adjust the target value data with the first preset rule, and enter the received from adx After receiving the traffic, the step of sampling and selecting traffic from the traffic; if it is greater than or equal to the first threshold, then for the traffic other than the traffic selected by sampling, select advertisement data with target value data to generate a response and return to adx. Thus, the beneficial effect of adjusting the target value data according to the basis and improving the success rate of the target value data participating in the bidding is obtained.

Moreover, in the embodiment of the present invention, before the traffic other than the traffic selected by sampling is selected with the target value data and the response is returned to adx, it is also possible to count the advertisement data with the target value data within the second time period Whether the number of successful competitions of the generated responses in adx is less than the second threshold; the second time period is greater than the first time period; at the same time, within the second time period, the responses generated with the target value data compete in adx Whether the number of successes is evenly distributed; and after the target value data is used to select the advertising data generation response and return it to adx for traffic other than the traffic selected by sampling, it can also be judged that the target value data generation response is followed by any first time In the segment, whether the number of successful competitions in adx generated by the target value data is less than the third threshold, so as to further improve the validity of the adjusted target value data.

Embodiment five

A flow response device provided by an embodiment of the present invention is introduced in detail.

Referring to FIG. 5 , it shows a schematic structural diagram of a traffic response device in an embodiment of the present invention.

The device 500 includes:

The memory 510 is loaded with multiple executable instructions;

The processor 520 executes the multiple executable instructions; the multiple executable instructions include a method for performing the following steps:

After the traffic received from adx, select traffic by sampling from said traffic;

For the traffic selected by sampling, select the advertising data with the target value data to generate a response and return it to adx;

Statistics within the first period of time, whether the number of times the response generated by the target value data successfully competes in adx is less than the first threshold;

If it is less than the first threshold, then adjust the target value data with the first preset rule, enter the step of sampling and selecting the flow from the flow after receiving the flow from adx;

If it is greater than or equal to the first threshold, for traffic other than the traffic selected by sampling, select advertisement data with target value data to generate a response and return it to adx.

In the embodiment of the present invention, after the traffic received from adx, the traffic can be sampled and selected from the traffic; for the traffic selected by sampling, the advertisement data generation response is selected with the target value data and returned to adx; the statistics are at the first time In the section, whether the number of successful competitions in adx generated by the target value data is less than the first threshold; if it is less than the first threshold, then adjust the target value data with the first preset rule, and enter the received from adx After receiving the traffic, the step of sampling and selecting traffic from the traffic; if it is greater than or equal to the first threshold, then for the traffic other than the traffic selected by sampling, select advertisement data with target value data to generate a response and return to adx. Thus, the beneficial effect of adjusting the target value data according to the basis and improving the success rate of the target value data participating in the bidding is obtained.

Moreover, in the embodiment of the present invention, before the traffic other than the traffic selected by sampling is selected with the target value data and the response is returned to adx, it is also possible to count the advertisement data with the target value data within the second time period Whether the number of successful competitions of the generated responses in adx is less than the second threshold; the second time period is greater than the first time period; at the same time, within the second time period, the responses generated with the target value data compete in adx Whether the number of successes is evenly distributed; and after the target value data is used to select the advertising data generation response and return it to adx for traffic other than the traffic selected by sampling, it can also be judged that the target value data generation response is followed by any first time In the segment, whether the number of successful competitions in adx generated by the target value data is less than the third threshold, so as to further improve the validity of the adjusted target value data.

As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for related parts, please refer to the part of the description of the method embodiment.

The algorithms and displays presented herein are not inherently related to any particular computer, virtual system, or other device. Various generic systems can also be used with the teachings based on this. The structure required to construct such a system is apparent from the above description. Furthermore, the present invention is not specific to any particular programming language. It should be understood that various programming languages can be used to implement the content of the present invention described herein, and the above description of specific languages is for disclosing the 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 the understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, in order to streamline this disclosure and to facilitate an understanding of one or more of the various inventive aspects, various features of the invention are sometimes grouped together in a single embodiment, figure, or its description. This method of disclosure, however, is not to be interpreted as reflecting an intention that 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 can understand that the modules in the device in the embodiment can be adaptively changed and arranged in one or more devices different from the embodiment. Modules or units or components in the embodiments may be combined into one module or unit or component, and furthermore may be divided into a plurality of sub-modules or sub-units or sub-assemblies. All features disclosed in this specification (including accompanying claims, abstract and drawings) and any method or method so disclosed may be used in any combination, except that at least some of such features and/or processes or units are mutually exclusive. All processes or units of equipment are combined. Each feature disclosed in this specification (including 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 understand that although some embodiments described herein include some features included in other embodiments but not others, combinations of features from 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 may be used in any combination.

The various component embodiments of the present 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 should understand that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all functions of some or all components in the flow response device according to the embodiment of the present invention. The present invention can also be implemented as an apparatus or an apparatus program (for example, a computer program and a computer program product) for performing a part or all of the methods described herein. Such a program for realizing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet site, or 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 can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means can be embodied by one and the same item of hardware. The use of the words first, second, and third, etc. does not indicate any order. These words can be interpreted as names.

This application discloses A1, a traffic response method, including:

After receiving traffic from an ad exchange, sampling traffic from said traffic;

For the traffic selected by sampling, select advertising data with target value data to generate a response and return it to the advertising exchange platform;

Counting whether the number of times the responses generated with the target value data successfully compete in the advertising exchange platform within the first period of time is less than the first threshold;

If it is less than the first threshold, adjust the target value data according to the first preset rule, and enter the step of sampling and selecting traffic from the traffic received from the advertising trading platform;

If it is greater than or equal to the first threshold, for the flow other than the flow selected by sampling, select the advertisement data with the target value data to generate a response and return it to the advertisement exchange platform.

A2. The method as described in A1, the step of adjusting the target value data according to the first preset rule includes:

According to the dichotomy rule, the last target value data is adjusted.

A3. The method as described in A1, before the step of selecting advertising data with target value data to generate a response and returning it to the advertising trading platform for traffic other than the traffic selected by sampling, further includes:

Count whether the number of times the responses generated by the target value data successfully compete in the advertising exchange platform within the second time period is less than a second threshold; the second time period is greater than the first time period;

If it is less than the second threshold, adjust the target value data according to the first preset rule, and enter the step of sampling and selecting traffic from the traffic received from the advertising trading platform.

A4. The method as described in A1, before the step of selecting advertising data with target value data to generate a response and returning it to the advertising trading platform for traffic other than the traffic selected by sampling, further includes:

Statistics within the second time period, whether the number of times the responses generated by the target value data are successfully distributed in the advertising trading platform is evenly distributed; the second time period is greater than the first time period;

If the distribution is uneven, the target value data is adjusted according to a first preset rule, and the step of sampling and selecting traffic from the traffic received from the advertising trading platform is entered.

A5. The method as described in A1, the step of sampling and selecting traffic from the traffic after receiving the traffic from the advertising exchange platform includes:

After receiving the traffic from the advertising trading platform, according to the dimension to which the traffic belongs, the traffic of the same dimension is sampled and selected.

A6. The method as described in A5, the step of selecting advertising data with target value data to generate a response and returning it to the advertising exchange platform for traffic other than the traffic selected by sampling, including:

For the flow of the same dimension other than the flow selected by sampling, the target value data is used to select the advertisement data to generate a response and return it to the advertising exchange platform.

A7. The method as described in A1, after the step of selecting advertisement data with target value data to generate a response and returning it to the advertising trading platform for traffic other than the traffic selected by sampling, further includes:

Judging whether the number of successful competitions of the responses generated with the target value data in the advertising exchange platform within any first time period following the generation of the target value data is less than the third threshold;

If it is not less than the third threshold, stop entering the traffic other than the traffic selected for sampling, select the advertising data with the target value data to generate a response and return to the advertising exchange platform, and reduce the target value data with the second preset rule, enter The step of selecting traffic by sampling from the traffic received from the advertising exchange platform.

A8. The method as described in A5, wherein the dimension division parameters include at least one of advertisement position attributes, user attributes, and user interest dimensions.

This application also discloses B9, a flow response device, comprising:

A traffic sampling selection module, configured to sample and select traffic from the traffic received from the advertising trading platform;

The first response generation and return module is used for selecting the advertisement data with the target value data to generate a response and return it to the advertisement exchange platform for the traffic selected by the sampling;

The first counting module for the number of successful competitions is used to count whether the number of successful competitions in the advertising trading platform for the responses generated with the target value data within the first time period is less than the first threshold;

The first target value data adjustment module is used to adjust the target value data according to the first preset rule if it is less than the first threshold, and then enter the traffic sampling selection module;

The second response generating and returning module is configured to select advertisement data with target value data to generate a response to the advertising exchange platform for traffic other than the traffic selected by sampling if it is greater than or equal to the first threshold.

B10, the device as described in B9, the first target value data adjustment module includes:

The target value data adjustment sub-module is used to adjust the last target value data by dichotomy rule.

B11, the device as described in B9, before the second response is generated and returned to the module, it also includes:

The second statistical module for the number of successful competitions is used to count whether the number of successful competitions in the advertising exchange platform generated by the response generated with the target value data within the second time period is less than the second threshold; the second time period is greater than the second threshold A period of time; if it is less than the second threshold, enter the first target value data adjustment module.

B12, the device as described in B9, before the second response is generated and returned to the module, it also includes:

The competition success uniform judgment module is used to count whether the number of times of successful competition in the advertising trading platform for the responses generated by the target value data is evenly distributed within the second time period; the second time period is greater than the first time period; If the distribution is uneven, enter the first target value data adjustment module.

B13, the device as described in B9, the flow sampling selection module includes:

The traffic sampling selection sub-module is also used to sample and select traffic from the traffic of the same dimension according to the dimension of the traffic received from the advertising trading platform.

B14. The device as described in B13, the second response generating and returning module is further configured to select advertising data with target value data to generate a response to the advertising trading platform for traffic of the same dimension other than the traffic selected by sampling.

B15. The device as described in B9, after the second response is generated and returned to the module, further includes:

The third statistical module for the number of successful competitions is used to judge whether the number of successful competitions in the advertising exchange platform for the response generated by the target value data is less than the third threshold;

The second target value data adjustment module is used to stop entering the traffic other than the traffic selected for sampling if it is not less than the third threshold, select the advertising data with the target value data to generate a response and return to the advertising exchange platform, and use the first The second preset rule reduces the target value data and enters the traffic sampling selection module.

B16. The device according to B13, wherein the dimension division parameters include at least one of advertisement space attributes, user attributes, and user interest dimensions.

This application also discloses C17, a flow response device, including:

The memory is loaded with multiple executable instructions;

A processor that executes the plurality of executable instructions; the plurality of executable instructions includes a method for performing the following steps:

After receiving traffic from an ad exchange, sampling traffic from said traffic;

For the traffic selected by sampling, select advertising data with target value data to generate a response and return it to the advertising exchange platform;

Counting whether the number of times the responses generated with the target value data successfully compete in the advertising exchange platform within the first period of time is less than the first threshold;

If it is less than the first threshold, adjust the target value data according to the first preset rule, and enter the step of sampling and selecting traffic from the traffic received from the advertising trading platform;

If it is greater than or equal to the first threshold, for the flow other than the flow selected by sampling, select the advertisement data with the target value data to generate a response and return it to the advertisement exchange platform.

Claims (10)

1. A traffic response method, comprising: After receiving traffic from an ad exchange, sampling traffic from said traffic; For the traffic selected by sampling, select advertising data with target value data to generate a response and return it to the advertising exchange platform; Counting whether the number of times the responses generated with the target value data successfully compete in the advertising exchange platform within the first period of time is less than the first threshold; If it is less than the first threshold, adjust the target value data according to the first preset rule, and enter the step of sampling and selecting traffic from the traffic received from the advertising trading platform; If it is greater than or equal to the first threshold, for the flow other than the flow selected by sampling, select the advertisement data with the target value data to generate a response and return it to the advertisement exchange platform. 2. The method according to claim 1, wherein the step of adjusting the target value data with a first preset rule comprises: According to the dichotomy rule, the last target value data is adjusted. 3. The method according to claim 1, characterized in that, before the step of selecting advertising data with target value data to generate a response and returning it to the advertising exchange platform for traffic other than the traffic selected by sampling, it also includes: Count whether the number of times the responses generated by the target value data successfully compete in the advertising exchange platform within the second time period is less than a second threshold; the second time period is greater than the first time period; If it is less than the second threshold, adjust the target value data according to the first preset rule, and enter the step of sampling and selecting traffic from the traffic received from the advertising trading platform. 4. The method according to claim 1, characterized in that, before the step of selecting advertisement data with target value data to generate a response and returning it to the advertising exchange platform for traffic other than the traffic selected by sampling, the method further includes: In the second time period, whether the distribution of the number of successful competitions of the responses generated by the target value data in the advertising exchange platform is even; the second time period is greater than the first time period; If the distribution is uneven, the target value data is adjusted according to a first preset rule, and the step of sampling and selecting traffic from the traffic received from the advertising trading platform is entered. 5. The method according to claim 1, wherein the step of sampling and selecting traffic from the traffic after receiving the traffic from the advertising trading platform includes: After receiving the traffic from the advertising trading platform, according to the dimension to which the traffic belongs, the traffic of the same dimension is sampled and selected. 6. The method according to claim 5, characterized in that, the step of selecting advertisement data with target value data to generate a response and returning it to the advertisement exchange platform for traffic other than the traffic selected by sampling includes: For the flow of the same dimension other than the flow selected by sampling, the target value data is used to select the advertisement data to generate a response and return it to the advertising exchange platform. 7. The method according to claim 1, characterized in that, after the step of selecting advertising data with target value data to generate a response and returning it to the advertising exchange platform for traffic other than the traffic selected by sampling, it also includes: Judging whether the number of successful competitions of the responses generated with the target value data in the advertising exchange platform within any first time period subsequent to the generation of the target value data is less than the third threshold; If it is not less than the third threshold, stop entering the traffic other than the traffic selected for sampling, select the advertising data with the target value data to generate a response and return to the advertising exchange platform, and reduce the target value data with the second preset rule, enter The step of selecting traffic by sampling from the traffic received from the advertising exchange platform. 8 . The method according to claim 5 , wherein the dimension division parameters include at least one of advertising space attributes, user attributes, and user interest dimensions. 9. A flow responsive device comprising: A traffic sampling selection module, configured to sample and select traffic from the traffic received from the advertising trading platform; The first response generation and return module is used to select the advertisement data with the target value data to generate a response and return it to the advertisement trading platform for the traffic selected by the sampling; The first counting module for the number of successful competitions is used to count whether the number of successful competitions in the advertising trading platform for the responses generated with the target value data within the first time period is less than the first threshold; The first target value data adjustment module is used to adjust the target value data according to the first preset rule if it is less than the first threshold, and then enter the traffic sampling selection module; The second response generating and returning module is configured to select advertisement data with target value data to generate a response to the advertising exchange platform for traffic other than the traffic selected by sampling if it is greater than or equal to the first threshold. 10. A flow responsive device comprising: The memory is loaded with multiple executable instructions; A processor that executes the plurality of executable instructions; the plurality of executable instructions includes a method for performing the following steps: After receiving traffic from an ad exchange, sampling traffic from said traffic; For the traffic selected by sampling, select advertising data with target value data to generate a response and return it to the advertising exchange platform; Counting whether the number of times the responses generated with the target value data successfully compete in the advertising exchange platform within the first period of time is less than the first threshold; If it is less than the first threshold, adjust the target value data according to the first preset rule, and enter the step of sampling and selecting traffic from the traffic received from the advertising trading platform; If it is greater than or equal to the first threshold, for the flow other than the flow selected by sampling, select the advertisement data with the target value data to generate a response and return it to the advertisement exchange platform.