CN113011927B

CN113011927B - Information delivery method and device, electronic equipment and storage medium

Info

Publication number: CN113011927B
Application number: CN202110352194.1A
Authority: CN
Inventors: 张宇; 徐开胜
Original assignee: Beijing QIYI Century Science and Technology Co Ltd
Current assignee: Beijing QIYI Century Science and Technology Co Ltd
Priority date: 2021-03-31
Filing date: 2021-03-31
Publication date: 2023-10-13
Anticipated expiration: 2041-03-31
Also published as: CN113011927A

Abstract

The application relates to an information delivery method, an information delivery device, electronic equipment and a storage medium. The method is applied to the technical field of data processing, wherein the information delivery method comprises the following steps: acquiring flow data of information to be processed in a first preset time period; according to the flow data, determining a first adjustment value of the information to be processed, wherein the first adjustment value is used for indicating the stability of a delivery coefficient of the information to be processed; when the first adjustment value indicates that the delivery coefficient is unstable, smoothing the first adjustment value to obtain a second adjustment value; and based on the second adjustment value and the release coefficient, releasing the information to be processed. In the related art, the value adjustment quantity is directly used for evaluating the advertisement, the value of the advertisement is directly influenced, and when the value adjustment quantity fluctuates greatly, the evaluation result is unstable, so that the problem that the matching degree of the advertisement and a user is influenced due to unreasonable advertisement resource allocation in the personalized advertisement recommendation process is solved.

Description

Information delivery method and device, electronic equipment and storage medium

Technical Field

The present application relates to the field of data processing technologies, and in particular, to an information delivery method, an information delivery device, an electronic device, and a storage medium.

Background

With the rapid development of internet technology, advertisers are enabled to accurately deliver advertisements by using an internet platform. The advertising system maximizes the advertiser's remaining resources and user experience by delivering advertisements of greatest interest to different populations.

When advertisements are placed, value evaluation of the advertisements is required. In the related art, when evaluating the advertisement value, it is necessary to sense the current value of the advertisement in real time and obtain the value adjustment amount of the advertisement, thereby obtaining the evaluation value of the advertisement. However, since the value adjustment quantity is directly used for evaluating the advertisement, the value of the advertisement is directly influenced, and when the value adjustment quantity fluctuates greatly, the evaluation result is unstable, so that the advertisement resource allocation is unreasonable in the personalized advertisement recommendation process, and the matching degree of the advertisement and the user is influenced.

Disclosure of Invention

The application provides an information delivery method, an information delivery device, electronic equipment and a storage medium, which are used for solving the problems that in the related technology, the value adjustment quantity is directly used for evaluating advertisements, the value of the advertisements is directly influenced, and when the value adjustment quantity fluctuates greatly, the evaluation result is unstable, and further, in the personalized advertisement recommendation process, the advertisement resource allocation is unreasonable, and the matching degree between the advertisements and users is influenced.

In a first aspect, the present application provides an information delivery method, including:

acquiring flow data of information to be processed in a first preset time period;

determining a first adjustment value of the information to be processed according to the flow data, wherein the first adjustment value is used for indicating the stability of a delivery coefficient of the information to be processed;

when the first adjustment value indicates that the delivery coefficient is unstable, smoothing the first adjustment value to obtain a second adjustment value;

and based on the second adjustment value and the release coefficient, releasing the information to be processed.

In a second aspect, the present application provides an information delivery apparatus, including:

the acquisition module is used for acquiring flow data of the information to be processed in a first preset time period;

the determining module is used for determining a first adjustment value of the release coefficient of the information to be processed according to the flow data, wherein the first adjustment value is used for reflecting the stability of the release coefficient of the information to be processed;

the smoothing module is used for carrying out smoothing treatment on the first adjustment value to obtain a second adjustment value when the first adjustment value indicates that the delivery coefficient is unstable;

And the release module is used for releasing the information to be processed based on the second adjustment value and the release coefficient.

In a third aspect, the present application provides an electronic device, comprising: the device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus; the memory is used for storing a computer program; the processor is configured to execute the program stored in the memory, and implement the information delivery method according to the first aspect.

In a fourth aspect, the present application provides a computer readable storage medium storing a computer program, which when executed by a processor implements the information delivery method according to the first aspect.

Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages: according to the method provided by the embodiment of the application, after the flow data of the information to be processed in the first preset time period are obtained, the first adjustment value of the throwing coefficient of the information to be processed is determined according to the flow data, and the first adjustment value is used for reflecting the stability of the throwing coefficient of the information to be processed, so that when the first adjustment value indicates that the throwing coefficient is unstable, the first adjustment value is subjected to smoothing processing to obtain the second adjustment value, and therefore, before the information throwing of the information to be processed is carried out, if the throwing coefficient is determined to be unstable, the first adjustment value is subjected to smoothing processing, and the problem of inaccurate throwing of the information to be processed caused by directly applying the first adjustment value to the information throwing is avoided; in addition, after the first adjustment value is smoothed to obtain the second adjustment value, information is put in the information to be processed based on the second adjustment value and the put-in coefficient, the condition that the information to be processed is distributed unreasonably is avoided, and the accuracy of information put in the information to be processed is improved.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.

FIG. 1 is a schematic diagram of an application architecture of an information delivery method according to an embodiment of the present application;

FIG. 2 is a flow chart of a method for information delivery in an embodiment of the application;

FIG. 3 is a flow chart of a method for information delivery according to another embodiment of the present application;

FIG. 4 is a flow chart of a method for information delivery according to another embodiment of the present application;

FIG. 5 is a schematic diagram of an information delivery device according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the application.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application.

According to an embodiment of the application, an information delivery method is provided. Alternatively, in the embodiment of the present application, the above information delivery method may be applied to a hardware environment formed by the terminal 101 and the server 102 as shown in fig. 1. As shown in fig. 1, the server 102 is connected to the terminal 101 through a network, which may be used to provide services (such as video services, application services, etc.) to the terminal or clients installed on the terminal, and a database may be provided on the server or independent of the server, for providing data storage services to the server 102, where the network includes, but is not limited to: the terminal 101 is not limited to a PC, a mobile phone, a tablet computer, or the like.

The information delivery method according to the embodiment of the present application may be executed by the server 102 or by the terminal 101. The terminal 101 executes the information delivery method according to the embodiment of the present application, specifically, by the client installed thereon.

Taking the terminal to execute the information delivery method according to the embodiment of the present application as an example, fig. 2 is a schematic flow chart of an alternative information delivery method according to the embodiment of the present application, as shown in fig. 2, the flow of the method may include the following steps:

step 201, obtaining flow data of information to be processed in a first preset time period.

In some embodiments, the traffic data acquired by the terminal may be stored locally by the terminal, or may be acquired by the terminal from a database of the server, or may be acquired by the terminal from an upstream engine interface.

The information to be processed is various, for example, advertisement, video, commodity or novel. The traffic data may, but is not limited to, delivery outcome data including user data and/or information to be processed. Specifically, the user data includes, but is not limited to, at least one of: user portrait information or operation information of the user to the information to be processed. Wherein the operational information includes, but is not limited to, at least one of click, collection, comment, download, or payment information.

The first preset time period may be set according to actual situations, and is not limited herein, for example, the first preset time period is one day, one week, 6 hours, and the like, and may be set in a self-defined manner.

Further, the flow data in the first preset time period of the information to be processed may be obtained by first obtaining the original data in the first preset time period of the information to be processed, and then preprocessing (such as data filtering, cleaning, aggregation, etc.) the original data to obtain the flow data. Specifically, the original data acquired by the terminal is the data which is not processed by the upstream engine interface, and after the original data is acquired, useless data (such as order numbers of information to be processed and the like) for adjusting the information input coefficient to be processed are required to be removed; in addition, in the cleaned original data, the rest data is aggregated, so that the flow data is obtained.

Step 202, determining a first adjustment value of the information to be processed according to the flow data, wherein the first adjustment value is used for indicating stability of a delivery coefficient of the information to be processed.

In some embodiments, the traffic data includes user data and delivery data of the information to be processed, and after the terminal obtains the traffic data, the first adjustment value of the information to be processed can be determined according to the user data and the delivery data through a corresponding adjustment model.

Wherein the information to be processed may include, but is not limited to: at least one of advertising information, video, merchandise applications. And the release coefficient of the information to be processed is used for indicating the value of the information to be processed.

For example, when the information to be processed is an advertisement, the delivery coefficient of the advertisement is used to indicate the value of the advertisement, and the actual scene can be specifically expressed as at least one of the following: the bid for the advertisement, the revenue for the advertisement, the click-through rate for the advertisement, the conversion rate for the advertisement, the play data for the video associated with the advertisement, etc., to which embodiments of the present invention are not particularly limited.

For example, when the information to be processed is video, the release coefficient of the video is used to indicate the value of the video, and the actual scene may be specifically expressed as at least one of the following: the number of plays of the video, the number of comments of the video, the bid of the video, the value of the advertisement associated with the video, etc., which is also not particularly limited in the embodiments of the present invention.

For example, when the information to be processed is an application, the release coefficient of the application is used to indicate the value of the application, and the actual scenario may be specifically expressed as at least one of the following: the number of downloads of an application, the frequency of opening of an application, the bid of an application, the value of an advertisement associated with an application, etc., which are also not particularly limited by the embodiments of the present invention.

For example, when the information to be processed is a commodity, the release coefficient of the commodity is used to indicate the value of the commodity, and the actual scene can be specifically expressed as at least one of the following: the amount of purchase of the commodity, the stock value of the commodity, the bid of the commodity, the evaluation of the commodity by the user, the value of the advertisement associated with the commodity, and the like, which is not particularly limited in the embodiment of the present invention.

Whether the throwing coefficient of the information to be processed is stable or not is closely related to whether the information to be processed can be stably thrown or not.

In an exemplary embodiment, taking a bid with a delivery coefficient as an advertisement as an example, the first adjustment value indicates an adjustment value for the bid for the advertisement. When the first adjustment value of the advertisement is too large or too small, the bid of the current advertisement is excessively large or too small, so that the bid of the advertisement is relatively dynamic. In practical application, if the bid of the advertisement is always over-high, the advertisement is caused to be over-high, so that the delivery of the advertisement is reduced; if the bid of the advertisement is too small, the advertisement is increased due to the too small bid, and the advertisement is influenced whether the bid is too large or too small, so that the benefits of advertisers are lost. Accordingly, the bid of an advertisement needs to be maintained within a stable range to ensure stability of delivery of the advertisement and the benefit of the advertiser.

Based on the above related embodiments, the flow data includes user data and delivery result data, after the information to be processed is delivered, the delivery result after the information to be processed is delivered is obtained, and since the total delivery coefficient of the information to be processed is fixed, the stability of the subsequent delivery coefficient of the information to be processed is affected by each delivery coefficient. In addition, since the user data affects the next delivery result of the information to be processed, the first adjustment value can be determined through the flow data.

And 203, when the first adjustment value indicates that the delivery coefficient is unstable, performing smoothing processing on the first adjustment value to obtain a second adjustment value.

In some embodiments, in order to avoid that when information to be processed is put in, the situation of explosion or drop occurs in the put-in result due to the severe change of the first adjustment value, so that the information to be processed is distributed unreasonably, and therefore, before information is put in based on the first adjustment value, the stability of the put-in coefficient is judged first.

When the first adjustment value indicates that the delivery coefficient is unstable, the first adjustment value can be subjected to smoothing treatment to obtain a second adjustment value, so that the situation that the information to be processed is delivered inaccurately due to the fact that the first adjustment value is too large or too small is reduced.

And 204, based on the second adjustment value and the release coefficient, releasing the information to be processed.

In some embodiments, after the second adjustment value is obtained by smoothing the first adjustment value, information may be put into the information to be processed based on the smoothed second adjustment value and the put coefficient. Therefore, the situation that the explosion quantity or the drop quantity is caused by directly adopting the first adjustment value to carry out information delivery is avoided.

In this embodiment, after flow data of information to be processed in a first preset period of time is obtained, a first adjustment value of a delivery coefficient of the information to be processed is determined according to the flow data, and because the first adjustment value is used for reflecting stability of the delivery coefficient of the information to be processed, when the first adjustment value indicates that the delivery coefficient is unstable, smoothing is performed on the first adjustment value to obtain a second adjustment value, so that before the information delivery of the information to be processed is performed, if the delivery coefficient is determined to be unstable, the first adjustment value is smoothed, thereby avoiding the problem of inaccurate delivery of the information to be processed caused when the first adjustment value is directly applied to the information delivery; in addition, after the first adjustment value is smoothed to obtain the second adjustment value, information is put in the information to be processed based on the second adjustment value and the put-in coefficient, the condition that the information to be processed is distributed unreasonably is avoided, and the accuracy of information put in the information to be processed is improved.

In an alternative embodiment, the first adjustment value indicates that the stability of the delivery coefficient may be determined by setting a corresponding stability interval.

Specifically, when the first adjustment value is in the stable interval, determining that the first adjustment value indicates that the input coefficient of the information to be processed is stable; and when the first adjustment value is not in the stable interval, determining that the first adjustment value indicates that the delivery coefficient of the information to be processed is unstable.

The stability interval may be set to [1-X,1+x ], where X refers to a stability interval range, and a specific value of X may be set according to an actual situation, which is not limited herein.

In an alternative embodiment, the stability interval range may be set to a specific value, e.g., stability interval range of 0.2, then the corresponding stability interval is [0.8,1.2].

In another alternative embodiment, the process of determining the stability interval may be implemented by: and acquiring a section adjustment coefficient, wherein the section adjustment coefficient is used for indicating the adjustment amount of a target section, and the target section is a stable section used for the last adjustment after information is put in by using the target section and is determined according to the obtained first put-in result. Then, the target section is adjusted according to the section adjustment coefficient, and a stable section is obtained.

Specifically, in some embodiments, the information is put in the target interval, which may specifically be that in step 203, the stability of the first adjustment value is determined by using the target interval, so as to obtain the second adjustment value, and the information to be processed is put in the target interval according to the steps 201 to 204, so as to obtain the first put result obtained after the information is put in the target interval. After the first delivery result is determined, a section adjustment coefficient is determined according to the first delivery result.

It will be appreciated that the target adjustment is due to the initial adjustment factor being preset before the adjustment.

In some embodiments, the interval adjustment coefficient is used to indicate the adjustment amount of the target adjustment factor interval, so after obtaining the interval adjustment coefficient, the target interval can be adjusted by the interval adjustment coefficient, so as to obtain a new stable interval. After the new stable section is obtained, the difference between the new stable section and the target section is compared, and when the new stable section and the target section are identical, the new stable section is taken as the final stable section.

The process of adjusting the target section by the section adjustment coefficient is to add the target section and the section adjustment coefficient, and the obtained sum is used as a new stable section. It is understood that the interval adjustment coefficient actually obtained may be positive or negative.

In this embodiment, when determining the stable section, the section adjustment coefficient is obtained after information is put in based on the last stable section, and the target section is adjusted. Therefore, the stability interval of the information to be processed is determined according to the performance of the throwing result in the throwing process, the obtained stability interval is more accurate, the stability of the throwing coefficient indicated by the first adjusting value is more accurate, and the accuracy of information throwing of the information to be processed is improved.

Further, based on the content of the above embodiments, as an alternative embodiment: smoothing the first adjustment value to obtain a second adjustment value, including:

acquiring a third adjustment value of the information to be processed; wherein, the third adjustment value is: an adjustment value of the same dimension as the first adjustment value and the last time; the second adjustment value is determined based on a first magnitude relation between the third adjustment value and the first adjustment value.

In this embodiment, by comparing the first adjustment value with the third adjustment value, since the third adjustment value is the same as the first adjustment value in dimension and is the last adjustment value, the smooth amplitude of the first adjustment value can be determined according to the magnitude of the third adjustment value, and further the second adjustment value can be determined.

Wherein the dimension includes at least one of a drop location or a data acquisition mode. The drop position may be, but is not limited to, a power-on interface, a pause interface, a payment interface, and the like.

The data may be obtained in a manner that is not limited to the type of adjustment model. The adjustment model is a model used in determining the first adjustment value. The types of adjustment models include experimental adjustment models and control adjustment models. Before the experimental adjustment model is applied to the line, information to be processed is respectively put in through the experimental adjustment model and the contrast adjustment model, and then the experimental adjustment model and the contrast adjustment model are used for carrying out model adjustment according to respective put-in results.

When the first adjustment value is determined using the adjustment model, the flow data acquired in step 201 is input into the adjustment model, calculated by the adjustment model, and output to obtain the first adjustment value. In addition to directly acquiring the first adjustment value through the trained adjustment model, other acquisition modes are provided in the embodiments of the present invention, which will be described in detail later.

In some embodiments, the above-mentioned determination of the second adjustment value based on the first magnitude relation between the third adjustment value and the first adjustment value may be implemented in the following alternative embodiments.

According to the first magnitude relation, determining an intermediate coefficient, wherein the intermediate coefficient is an operation value between a third adjustment value and an adjustment factor, and the operation value is at least one of a difference value, a sum value or a product; wherein the adjustment factor is used to indicate an adjustment amplitude between adjacent adjustment values; a second adjustment value is determined based on a second magnitude relation between the first adjustment value and the intermediate coefficient.

In an alternative embodiment, the determined intermediate coefficients are different when the magnitude relation between the third adjustment value and the first adjustment value is different. Further, the second adjustment value is different from the second adjustment value determined based on the second magnitude relation between the first adjustment value and the intermediate coefficient.

The operation mode between the third adjustment value and the adjustment factor can be determined according to the value of the adjustment factor. For example, where the adjustment factor is a percentage, the operand may be a product; when the adjustment factor is an adjustment amount, the operation value may be a sum value or a difference value.

In one aspect, when the third adjustment value is greater than the first adjustment value, a difference between the third adjustment value and the adjustment factor is used as an intermediate coefficient, and then a maximum value between the first adjustment value and the intermediate coefficient is used as the second adjustment value.

The process of determining the second adjustment value is specifically described, for example, when the third adjustment value is greater than the first adjustment value. When the third adjustment value is greater than the first adjustment value, the first operation value may be set as the difference value. Since the adjustment factor is used to indicate the adjustment amplitude between the adjacent adjustment values, if the third adjustment value is greater than the first adjustment value, the difference between the third adjustment value and the adjustment factor is calculated to obtain an intermediate coefficient, and then the maximum value between the intermediate coefficient and the first adjustment value is used as the second adjustment value. Therefore, when the first adjustment value is smaller, smoothing can be performed through the intermediate coefficient, and the problem that information is put in to be processed and put in inaccuracy is caused by the fact that the first adjustment value is smaller and the first adjustment value is directly put in information is avoided.

On the other hand, when the third adjustment value is smaller than the first adjustment value, the sum of the third adjustment value and the adjustment factor is taken as an intermediate coefficient, and then the minimum value of the first adjustment value and the intermediate coefficient is taken as the second adjustment value.

The process of determining the second adjustment value is specifically described, for example, when the third adjustment value is smaller than the first adjustment value. When the third adjustment value is smaller than the first adjustment value, the first operation value may be set to a sum value. Because the adjustment factor is used for indicating the adjustment amplitude between the adjacent adjustment values, when the third adjustment value is smaller than the first adjustment value, the first adjustment value is larger at the moment, the difference value between the third adjustment value and the adjustment factor is calculated to obtain an intermediate coefficient, and then the minimum value between the intermediate coefficient and the first adjustment value is used as the second adjustment value. Therefore, when the first adjustment value is larger, smoothing can be performed through the intermediate coefficient, and the problem that information is put in to be processed and put in inaccuracy is caused by directly putting the first adjustment value into the information due to the fact that the first adjustment value is larger is avoided.

It can be understood that, in order to improve the accuracy of determining the second adjustment value, when the magnitude relation between the third adjustment value and the first adjustment value is different, different adjustment factors are set, so as to ensure that the second adjustment value is more accurate, and further, the information to be processed is put in more accurately.

In the case of determining the adjustment factor, the adjustment factor needs to be set according to the actual situation. For example, when the third adjustment value is smaller than the first adjustment value, if the adjustment factor is too small, the minimum value between the intermediate coefficient and the first adjustment value is the intermediate coefficient (the sum of the third adjustment value and the adjustment factor), and because the adjustment factor is too small, the second adjustment value is raised slowly, and the adjustment amplitude is too small, so that the time for increasing to the preset value is longer, and the delivery result is not ideal; if the adjustment factor is too large, the maximum value between the intermediate coefficient and the first adjustment value is the intermediate coefficient (the sum of the third adjustment value and the adjustment factor), and the second adjustment value is raised too quickly due to the too large adjustment factor, so that the smoothing effect is not obvious, and the explosion quantity and other conditions occur.

Based on the above embodiment, the above adjustment factor can be obtained by:

firstly, acquiring a factor adjustment coefficient, wherein the factor adjustment coefficient is used for indicating the adjustment amount of a target adjustment factor, the factor adjustment coefficient is determined according to an obtained second throwing result after information throwing is carried out by using the target adjustment factor, and the target adjustment factor is the adjustment factor used for the last time;

Secondly, adjusting the target adjustment factor according to the factor adjustment coefficient to obtain a current adjustment factor;

thirdly, obtaining the variable quantity between a second throwing result and a third throwing result, wherein the third throwing result is a throwing result obtained after information throwing by using the current adjustment factor;

fourth, the current adjustment factor when the variation is smaller than the preset value is used as the adjustment factor.

In this embodiment, when determining the current adjustment factor, the second delivery result obtained by delivering information based on the target adjustment factor used last time and the third delivery result obtained by delivering information using the current adjustment factor are the final adjustment factors determined by the variation of the second delivery result and the third delivery result. Therefore, the current adjustment factor when the first adjustment value of the information to be processed is smoothed is determined according to the performance of the throwing result in the throwing process, the obtained current adjustment factor is more accurate, the smoothing effect is more remarkable, the second adjustment value is more stable, and the accuracy of information throwing of the information to be processed is improved.

In some embodiments, the information delivery is performed according to the target adjustment factor, specifically, in step 203, the target adjustment factor is used to determine the second adjustment value, and the information to be processed is delivered according to the steps 201 to 204, so as to obtain a second delivery result obtained after the information is delivered by using the target adjustment factor. And after the second throwing result is determined, determining a factor adjustment coefficient according to the second throwing result.

It will be appreciated that the target adjustment factor is a pre-set initial adjustment factor before the adjustment is not made.

Further, the factor adjustment coefficient is used to indicate the adjustment amount of the target adjustment factor, so that after the factor adjustment coefficient is obtained, the target adjustment factor can be adjusted by the factor adjustment coefficient, so as to obtain a new adjustment factor, namely, the current adjustment factor.

And the process of obtaining the first adjustment factor by adjusting the target adjustment factor through the factor adjustment coefficient is to add the target adjustment factor and the factor adjustment coefficient, and take the obtained sum as the current adjustment factor. It will be appreciated that the factor adjustment coefficient may be positive or negative in practice.

In some embodiments, after obtaining the current adjustment factor, the terminal uses the first adjustment factor to perform information delivery, so as to obtain a third delivery result. And the variation of the delivery result is obtained by calculating the difference between the second delivery result and the third delivery result, so that the terminal can determine the stability of the delivery result according to the variation of the delivery result.

The process of determining the third delivery result may refer to the above-mentioned process of performing information delivery by using the target adjustment factor to obtain the relevant content of the second delivery result, which is not described herein again.

In some embodiments, the delivery result includes a throughput of the information to be processed, a total delivery coefficient, and a number of bursts of the information to be processed. Furthermore, the variation of the obtained delivery result comprises the difference value of the processing variable and the delivery coefficient of the information to be processed. In this case, when the adjustment factor is determined, the difference between the process variable and the delivery coefficient is made zero, and the current adjustment factor at the time when the number of bursts is the lowest is used as the adjustment factor.

Based on the above related embodiments, when determining the current adjustment factor, the second delivery result obtained by delivering information based on the target adjustment factor used last time, and the third delivery result obtained by delivering information using the current adjustment factor are determined as the final adjustment factor by the variation of the second delivery result and the third delivery result. Therefore, the current adjustment factor when the first adjustment value of the information to be processed is smoothed is determined according to the performance of the throwing result in the throwing process, the obtained current adjustment factor is more accurate, the second adjustment value is more stable, and the accuracy of information throwing of the information to be processed is improved.

In the above embodiment, the adjustment model is a calculation logic model for determining the first adjustment value from the flow data. And outputting the obtained first adjustment value by the adjustment model to obtain the adjustment value for the input coefficient of the information to be processed. Illustratively, when the information to be processed is an advertisement and the delivery coefficient is a bid for the advertisement, the first adjustment value is an adjustment value for the advertisement bid. Wherein, the bid of the advertisement is the unit price set by the advertiser before the advertisement is put in the information. When the first adjustment value indicates that the delivery coefficient is unstable, the last third adjustment value and the second adjustment value obtained by smoothing are all adjustment values for the unit price of the advertisement.

Further, when the first adjustment value is smoothed, the intermediate coefficient determined by the third adjustment value and the adjustment factor is compared with the first adjustment value to determine the second adjustment value. The adjustment factor ensures the stability of the difference between the adjustment values of two adjacent times, namely the difference does not exceed the size of the adjustment factor.

Further, when the stable section is determined, the target section is adjusted by the section adjustment coefficient. The interval adjustment coefficient is determined based on the obtained throwing result when the information is thrown by using the target interval.

Fig. 3 is a flowchart of an alternative information delivery method according to an embodiment of the present application, based on the content of the foregoing embodiments, as an alternative embodiment, determining, according to flow data, a first adjustment value of a delivery coefficient of information to be processed may include the following steps:

step 301, determining the type of delivery of the information to be processed.

In some embodiments, the delivery type is provided by a provider of the information to be processed, and the provider uploads the delivery type according to own requirements and obtains the delivery type from the terminal. Wherein the requirements of the supplier comprise clicking and/or downloading of the information to be processed, etc. Further, when the demand of the supplier is only one, for example, only the user needs to click or download the information to be processed, and the type of delivery is single demand delivery; when there are more than two requirements of the supplier, for example, the user is required to click and download the information to be processed, and the type of delivery is multi-requirement delivery.

Step 302, extracting target flow data consistent with the delivery type from the flow data, wherein the target flow data comprises user data and delivery result data of information to be processed.

In some embodiments, when the delivery types are different, the corresponding flow data is also different. After determining the release type of the information to be processed, extracting target flow data consistent with the release type from the flow data acquired in the first time period.

Based on the above-mentioned related embodiments, when the delivery type is single-demand delivery, the target flow data includes delivery result data obtained after executing the single demand and corresponding user data; when the delivery type is multi-demand delivery, the target flow data comprises delivery result data obtained after the multi-demand delivery is executed and corresponding user data.

The delivery result data comprises at least one of an actual total delivery coefficient and a residual delivery coefficient, and the processing amount of information to be processed.

Step 303, determining the delivery tendency of the information to be processed for information delivery according to the delivery result data.

In some embodiments, after the delivery result data of the information to be processed is obtained, whether the information to be processed continues to be delivered in the delivery tendency degree of the information to be processed can be determined according to the actual total delivery coefficient, the residual delivery coefficient and the processing amount of the information to be processed in the delivery result data.

Step 304, determining the processing tendency of the target user for processing the information to be processed according to the user data, wherein the target user is the user who currently acquires the information to be processed.

In some embodiments, after obtaining the user data, the processing degree of the information to be processed is different for each user, so that it can be determined according to the obtained user data, and the processing tendency degree of the target user of the current information to be processed on the information to be processed can be obtained.

In step 305, the product of the dispensing tendency and the processing tendency is obtained to obtain a first adjustment value.

Based on the above-mentioned related embodiments, after the delivery tendency and the processing tendency of the information to be processed are obtained, the product of the delivery tendency and the processing tendency is used as the first adjustment value.

For example, when the information to be processed is an advertisement, the placement tendency may be a probability that the advertisement is placed at a placement position, and the processing tendency may be a probability that the user operates the advertisement after the advertisement is placed.

Based on the above-mentioned related embodiments, the delivery tendency of the information to be processed for information delivery and the processing tendency of the user for processing the information to be processed are determined based on the target flow data consistent with the delivery type of the information to be processed. When the first adjustment value is determined, the influence of the information to be processed is considered, the influence of a user is considered, and the first adjustment value is determined by adopting the throwing tendency degree and the processing tendency degree together, so that the obtained first adjustment value is more accurate.

Based on the content of the above embodiments, the delivery result data includes: at least one of the actual total throwing coefficient and the residual throwing coefficient, and the processing amount of the information to be processed; as an alternative embodiment: according to the throwing result data, determining the throwing tendency of the information to be processed comprises the following steps:

obtaining the product of the throughput and the release coefficient to obtain a predicted total release coefficient;

obtaining a difference value between a predicted total release coefficient and an actual total release coefficient to obtain a release coefficient deviation value;

and determining the delivery tendency according to the delivery coefficient deviation value and the residual delivery coefficient, wherein the delivery tendency and the delivery coefficient deviation value form a positive correlation and a negative correlation with the residual delivery coefficient.

In this embodiment, when determining the tendency of the to-be-processed information, the tendency is determined based on the actual total input coefficient, the remaining input coefficient and the processing amount of the to-be-processed information in the input result, that is, the input result when the to-be-processed information was input the last time affects the input of this time. Therefore, when the information to be processed is put in again, the information is not put in randomly, but the current putting situation is determined according to the previous putting result, so that the determined putting tendency is more accurate. Further, the first adjustment value determined by the dispensing tendency is also more accurate.

Optionally, after information is put in the information to be processed, the terminal can directly obtain the processing amount, the actual total put coefficient and the residual put coefficient of the information to be processed from the system. The total release coefficient of the information to be processed by the provider is stored in the terminal, and the residual release coefficient can be obtained by the difference between the total release coefficient and the actual total release coefficient.

After the residual release coefficient is obtained and the release coefficient deviation value is determined, the release tendency can be obtained according to the function relation of the residual release coefficient and the release coefficient. The functional relationship between the release coefficient deviation value and the residual release coefficient may be set according to practical situations, and is not limited herein, for example, the functional relationship between the release coefficient deviation value and the residual release coefficient may be a quotient relationship.

Specifically, since the predicted total release coefficient represents the expected value of the supplier for the information to be processed, the smaller the release coefficient deviation value is, the smaller the release tendency of the information to be processed is, namely the release tendency and the release coefficient deviation value form a positive correlation.

Correspondingly, when information to be processed is put in, when the deviation value of the put-in coefficient is fixed, the smaller the residual put-in coefficient is, the larger the change is when the deviation value of the put-in coefficient is supplemented when the information to be processed is put in based on the residual put-in coefficient, and further, the greater the put-in tendency is; when the residual throwing coefficient is larger, when throwing is performed based on the residual throwing coefficient, the change is smaller when the throwing coefficient deviation value is supplemented, and then the throwing tendency is smaller, and the throwing tendency and the residual throwing coefficient form a negative correlation.

For example, taking the information to be processed as an advertisement, the actual total delivery coefficient and the residual delivery coefficient may be data of the same advertisement in different stages, the actual total delivery coefficient may be data consumed in the stage of delivering the advertisement, and the residual delivery coefficient is data to be consumed in the stage of continuing delivering the advertisement. The consumed data may be the value of the advertisement, and in practical application, may be the price, the showing times or the actual putting time of the advertisement. The amount of information to be processed may be, but is not limited to, the number of clicks, collections, and/or downloads performed by the user on the advertisement.

Based on the content of the above embodiments, as an alternative embodiment: according to the user data, determining the processing tendency of the target user to process the information to be processed, including:

according to the user data, calculating to obtain reference flow quality values of all users in a first preset time period, wherein the reference flow quality values are used for indicating average processing amount of information to be processed of the users;

estimating a target flow quality value of a target user;

and determining a processing tendency degree according to the ratio of the target flow quality value and the reference flow quality value, wherein the processing tendency degree is positively correlated with the ratio.

In this embodiment, the user data is analyzed, and the reference flow quality values of all users are compared with the flow quality of the target user and calculated, so as to determine the processing tendency of the target user to the information to be processed. Therefore, the "individual" (i.e., the target user) is analyzed based on the "population" (i.e., all users), so that the processing tendency of the target user in the processing of the information to be processed can be more accurate. Further, the first adjustment value determined by the dispensing tendency is also more accurate.

Alternatively, after determining the user data, the user data includes the processing amount of the information to be processed by each user, so that the average value of the processing amounts of the information to be processed by each user can be used as the reference traffic quality value. The terminal stores a pre-estimation model for pre-estimating the flow quality of the user, and a target flow quality value of a target user can be obtained through the pre-estimation model. And after the target flow quality value and the reference flow quality value are obtained, determining the processing tendency of the target user for processing the information to be processed according to the ratio of the target flow quality value and the reference flow quality value.

The processing tendency is proportional to the ratio of the target flow quality value to the reference flow quality value, namely, the larger the ratio is, the higher the processing amount of the target user for carrying out information processing on the information to be processed is, and the larger the processing tendency of the target user is.

Based on the foregoing, as an optional embodiment, the method further includes storing the second adjustment value in a preset storage system.

Specifically, after the second adjustment value is determined, in order to facilitate that the last adjustment value can be timely obtained when the first adjustment value is obtained for the next smoothing process, the second adjustment value is stored in the storage system and used as the third adjustment value for on-line access of the engine, so that flexible obtaining of the third adjustment value is ensured. Wherein the storage system may be, but is not limited to, redis.

According to the information throwing method, a smoothing processing module is added between control model reasoning and online pushing for calculating the first adjustment value, and the smoothing processing is carried out on the first adjustment value. The smoothing function is placed after the first adjustment value is calculated, so that the influence on the core control logic can be avoided; before the device is put on the wire for pushing, the first adjustment value with larger jitter can be smoothed in time, so that the stability of the on-wire throwing is improved.

The first adjustment value is subjected to smoothing treatment through the smoothing treatment module, so that the stability of on-line delivery is improved, and the uniform utilization of on-line flow is ensured; the problem of sudden drop and explosion quantity in the process of information to be processed is solved, and the accuracy rate, namely the effect of information to be processed is improved.

Fig. 4 is a flow chart of an alternative information delivery method according to an embodiment of the present application, and in a specific embodiment of the present application, referring to fig. 4, the information delivery method includes the following steps:

step 401, obtaining flow data of information to be processed.

Step 402, determining a first adjustment value of the information to be processed according to the flow data.

Step 403, determining whether the first adjustment value is within the stable interval, if so, executing step 406, and if not, executing step 404.

Step 404, obtaining a third adjustment value from the database, where the third adjustment value is: the same dimension as the first adjustment value and the last adjustment value.

Step 405, smoothing the first adjustment value based on the third adjustment value.

Step 406, obtaining a final adjustment value as a second adjustment value.

Step 407, pushing the second adjustment value onto the wire and storing the second adjustment value in the database.

In this embodiment, by setting the stability interval, when the first adjustment value is in the stability interval, the smoothing policy is not validated. Through the stable interval, the first adjustment value with smaller influence on the stability of the delivery system is screened out, the adjustment logic of the first adjustment value is avoided, the first adjustment value is ensured to timely feed back the delivery coefficient to the line while the larger influence on the delivery system is avoided, and the delivery effect of the information to be processed is effectively ensured.

In addition, when the first adjustment value is not in the stable section, a smoothing function is added between the control model generating the first adjustment value and the on-line push. After the smoothing function smoothes the first adjustment value, the core control logic can be prevented from being influenced; before the device is put on the wire for pushing, the first adjustment value with larger jitter can be smoothed in time, so that the stability of the on-wire throwing is improved. Thus, the first adjustment value outside the stable interval adopts smooth logic to avoid the first adjustment value from generating intense jitter. By limiting the variation amplitude of the first adjustment value, the stability of the delivery system is greatly improved, and the uniform utilization of the online flow data is ensured. In addition, the problems of sudden drop and explosion in the process of throwing the information to be processed are solved, and the throwing effect of the information to be processed is improved.

Based on the same conception, the embodiment of the application provides an information delivery device, the specific implementation of which can be referred to the description of the embodiment part of the method, and the repetition is omitted. As shown in fig. 5, the apparatus mainly includes:

an obtaining module 501, configured to obtain flow data of information to be processed in a first preset period of time;

The determining module 502 is configured to determine, according to the flow data, a first adjustment value of a delivery coefficient of the information to be processed, where the first adjustment value is used to reflect stability of the delivery coefficient of the information to be processed;

a smoothing module 503, configured to, when the first adjustment value indicates that the delivery coefficient is unstable, perform smoothing on the first adjustment value to obtain a second adjustment value;

and the releasing module 504 is configured to release information to be processed based on the second adjustment value and the releasing coefficient.

Optionally, the smoothing module 503 specifically includes:

the first acquisition unit is used for acquiring a third adjustment value of the information to be processed; wherein, the third adjustment value is: an adjustment value of the same dimension as the first adjustment value and the last time;

and a first determination unit configured to determine a second adjustment value based on a first magnitude relation between the third adjustment value and the first adjustment value.

Optionally, the first determining module includes:

the second determining unit is used for determining an intermediate coefficient according to the first magnitude relation, wherein the intermediate coefficient is an operation value between a third adjustment value and an adjustment factor, and the operation value is at least one of a difference value, a sum value or a product; wherein the adjustment factor is used to indicate an adjustment amplitude between adjacent adjustment values;

And a third determining unit configured to determine a second adjustment value based on a second magnitude relation between the first adjustment value and the intermediate coefficient.

Optionally, the apparatus further comprises:

and the fourth determining unit is used for determining that the first adjusting value indicates that the delivery coefficient of the information to be processed is unstable when the first adjusting value is not in the preset stable interval.

Optionally, the apparatus further comprises:

the second acquisition unit is used for acquiring an interval adjustment coefficient, wherein the interval adjustment coefficient is used for indicating the adjustment amount of a target interval, the interval adjustment coefficient is determined according to the obtained first throwing result after information throwing is carried out by using the target interval, and the target interval is a stable interval used for the last adjustment;

and the first adjusting unit is used for adjusting the target interval according to the interval adjusting coefficient to obtain a stable interval.

Optionally, the apparatus further comprises:

the third acquisition unit is used for acquiring a factor adjustment coefficient, wherein the factor adjustment coefficient is used for indicating the adjustment amount of a target adjustment factor, the factor adjustment coefficient is determined according to the obtained second delivery result after information delivery is carried out by using the target adjustment factor, and the target adjustment factor is the adjustment factor used for the last time;

The second adjusting unit is used for adjusting the target adjusting factor according to the factor adjusting coefficient to obtain the current adjusting factor;

the fourth acquisition unit is used for acquiring the variable quantity between the second delivery result and a third delivery result, wherein the third delivery result is a delivery result obtained after information delivery is performed by using the current adjustment factor;

and the fourth determining unit is used for taking the current adjustment factor when the variation is smaller than the preset value as the adjustment factor.

Optionally, the determining module includes:

a fifth determining unit, configured to determine a delivery type of the information to be processed;

the first extraction unit is used for extracting target flow data consistent with the delivery type from the flow data, wherein the target flow data comprises user data and delivery result data of information to be processed;

a sixth determining unit, configured to determine, according to the delivery result data, a delivery tendency of delivering information of the information to be processed;

a seventh determining unit, configured to determine, according to user data, a processing tendency of a target user for processing information to be processed, where the target user is a user who currently obtains the information to be processed;

and a fifth acquisition unit, configured to acquire a product of the dispensing tendency and the processing tendency, so as to obtain a first adjustment value.

Optionally, the delivering result data includes: at least one of the actual total throwing coefficient and the residual throwing coefficient, and the processing amount of the information to be processed;

a sixth determination unit including:

a sixth obtaining unit, configured to obtain a product of the throughput and the delivery coefficient, to obtain a predicted total delivery coefficient;

a seventh obtaining unit, configured to obtain a difference value between the predicted total delivery coefficient and the actual total delivery coefficient, to obtain a delivery coefficient deviation value;

and the eighth determining unit is used for determining the throwing tendency according to the throwing coefficient deviation value and the residual throwing coefficient, wherein the throwing tendency and the throwing coefficient deviation value form a positive correlation and a negative correlation with the residual throwing coefficient.

Optionally, the seventh determining unit includes:

the first calculation unit is used for calculating and obtaining reference flow quality values of all users in a first preset time period according to the user data, wherein the reference flow quality values are used for indicating the average processing amount of information to be processed of the users;

the first estimating unit is used for estimating a target flow quality value of a target user;

and a ninth determining unit for determining a processing tendency according to the ratio of the target flow quality value and the reference flow quality value, the processing tendency being positively correlated with the ratio.

Based on the same concept, the embodiment of the application also provides an electronic device, as shown in fig. 6, where the electronic device mainly includes: processor 601, communication interface 602, memory 603 and communication bus 604, wherein processor 601, communication interface 602 and memory 603 accomplish each other's communication through communication bus 604. The memory 603 stores a program executable by the processor 601, and the processor 601 executes the program stored in the memory 603 to implement the information delivery method described in any of the above embodiments.

The communication bus 604 mentioned in the above electronic device may be a peripheral component interconnect standard (Peripheral Component Interconnect, abbreviated to PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, abbreviated to EISA) bus, or the like. The communication bus 604 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in fig. 6, but not only one bus or one type of bus.

The communication interface 602 is used for communication between the electronic device and other devices described above.

The memory 603 may include random access memory (Random Access Memory, simply RAM) or may include non-volatile memory (non-volatile memory), such as at least one magnetic disk memory. Alternatively, the memory may be at least one memory device located remotely from the aforementioned processor 601.

The processor 601 may be a general-purpose processor including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), a digital signal processor (Digital Signal Processing, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a Field programmable gate array (Field-Programmable Gate Array, FPGA), or other programmable logic device, discrete gate or transistor logic device, or discrete hardware components.

In a further embodiment of the present application, there is also provided a computer-readable storage medium having stored therein a computer program which, when run on a computer, causes the computer to perform the information delivery method described in any of the above embodiments.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the processes or functions described in accordance with embodiments of the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, by a wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, microwave, etc.) means from one website, computer, server, or data center to another. The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape, etc.), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk), etc.

It should be noted that in this document, relational terms such as "first" and "second" and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

The foregoing is only a specific embodiment of the invention to enable those skilled in the art to understand or practice the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An information delivery method is characterized by comprising the following steps:

based on the second adjustment value and the release coefficient, information release is carried out on the information to be processed;

the smoothing processing is performed on the first adjustment value to obtain a second adjustment value, which includes:

acquiring a third adjustment value of the information to be processed; wherein, the third adjustment value is: an adjustment value that is the same dimension as the first adjustment value and that is the last time;

determining a second adjustment value based on a first magnitude relation between the third adjustment value and the first adjustment value;

wherein the determining the second adjustment value based on the first magnitude relation between the third adjustment value and the first adjustment value comprises:

according to the first magnitude relation, determining an intermediate coefficient, wherein the intermediate coefficient is an operation value between a third adjustment value and an adjustment factor, and the operation value is at least one of a difference value, a sum value or a product; wherein the adjustment factor is used to indicate an adjustment amplitude between adjacent adjustment values;

Determining a second adjustment value based on a second magnitude relation between the first adjustment value and the intermediate coefficient;

further comprises: acquiring a factor adjustment coefficient, wherein the factor adjustment coefficient is used for indicating the adjustment amount of a target adjustment factor, the factor adjustment coefficient is determined according to an obtained second throwing result after information throwing is carried out by using the target adjustment factor, and the target adjustment factor is the adjustment factor used for the last time;

according to the factor adjustment coefficient, adjusting the target adjustment factor to obtain a current adjustment factor;

acquiring the variable quantity between the second throwing result and a third throwing result, wherein the third throwing result is a throwing result obtained after information throwing by using the current adjustment factor;

and taking the current adjustment factor when the variation is smaller than a preset value as the adjustment factor.

2. The information delivery method according to claim 1, characterized in that the method further comprises:

and when the first adjustment value is not in the preset stable interval, determining that the first adjustment value indicates that the release coefficient of the information to be processed is unstable.

3. The information delivery method according to claim 2, characterized in that the method further comprises:

Acquiring a section adjustment coefficient, wherein the section adjustment coefficient is used for indicating the adjustment amount of a target section, the section adjustment coefficient is determined according to the obtained first throwing result after information throwing is carried out by using the target section, and the target section is a stable section used for the last adjustment;

and adjusting the target interval according to the interval adjustment coefficient to obtain the stable interval.

4. The information delivery method according to claim 1, wherein the determining, according to the flow data, a first adjustment value of a delivery coefficient of the information to be processed includes:

determining the type of the information to be processed;

extracting target flow data consistent with the release type from the flow data, wherein the target flow data comprises user data and release result data of the information to be processed;

determining the throwing tendency of the information to be processed for information throwing according to the throwing result data;

determining the processing tendency of a target user for processing the information to be processed according to the user data, wherein the target user is a user who currently acquires the information to be processed;

And obtaining the product of the throwing tendency degree and the processing tendency degree to obtain the first adjustment value.

5. The information delivery method according to claim 4, wherein the delivery result data includes: at least one of the actual total throwing coefficient and the residual throwing coefficient, and the processing amount of the information to be processed;

the determining the delivery tendency of the information to be processed according to the delivery result data comprises the following steps:

obtaining the product of the processing amount and the release coefficient to obtain a predicted total release coefficient;

obtaining a difference value between the predicted total release coefficient and the actual total release coefficient to obtain a release coefficient deviation value;

and determining the release tendency according to the release coefficient deviation value and the residual release coefficient, wherein the release tendency and the release coefficient deviation value form a positive correlation and a negative correlation.

6. The information delivery method according to claim 4, wherein the determining, according to the user data, a processing tendency of the target user to process the information to be processed includes:

according to the user data, calculating to obtain reference flow quality values of all users in the first preset time period, wherein the reference flow quality values are used for indicating the average processing amount of the information to be processed of the users;

Estimating a target traffic quality value of the target user;

and determining the processing tendency degree according to the ratio of the target flow quality value to the reference flow quality value, wherein the processing tendency degree is positively correlated with the ratio.

7. An information delivery apparatus, comprising:

the determining module is used for determining a first adjustment value of the delivery coefficient of the information to be processed according to the flow data, wherein the first adjustment value is used for indicating the stability of the delivery coefficient of the information to be processed;

the release module is used for releasing the information to be processed based on the second adjustment value and the release coefficient;

8. An electronic device, comprising: the device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;

the memory is used for storing a computer program;

the processor is configured to execute a program stored in the memory, and implement the information delivery method according to any one of claims 1 to 6.

9. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the information delivery method of any one of claims 1-6.