WO2023083316A1

WO2023083316A1 - Method and apparatus for establishing advertisement preference model, electronic device and storage medium

Info

Publication number: WO2023083316A1
Application number: PCT/CN2022/131462
Authority: WO
Inventors: 张勇; 赵磊
Original assignee: 深圳市酷开网络科技股份有限公司
Priority date: 2021-11-12
Filing date: 2022-11-11
Publication date: 2023-05-19
Also published as: CN114066514A

Abstract

Disclosed are a method and apparatus for establishing an advertisement preference model, an electronic device and a storage medium. The method for establishing an advertisement preference model comprises: analyzing advertisement exposure data and advertisement order data to determine the video completion rate and the bounce rate of an advertisement corresponding to an advertisement order identifier, wherein the advertisement exposure data is associated with the advertisement order data by means of the advertisement order identifier; and establishing an advertisement preference model on the basis of the advertisement order identifier, the video completion rate and the bounce rate. In the present disclosure, the advertisement exposure data and the advertisement order data which are associated by means of the advertisement order identifier are analyzed to determine the video completion rate and the bounce rate of the advertisement corresponding to the advertisement order identifier, so that the advertisement preference model is established according to the video completion rate and the bounce rate.

Description

Method, device, electronic device and storage medium for establishing advertisement preference model

References to related applications

This disclosure claims the priority of the invention patent with the application number 202111342422.3 and the invention name "method, device, electronic device and storage medium for establishing an advertising preference model" submitted to the State Intellectual Property Office of the People's Republic of China on November 12, 2021, Its entire contents are incorporated into this disclosure by reference.

field

The present disclosure generally relates to the communication field, and more particularly relates to a method, device, electronic device and storage medium for establishing an advertisement preference model.

background

OTT (Over The Top) is a very popular term in the communication industry. This term comes from basketball and other sports. reach the destination. That is, Internet companies surpass operators and develop various video and data service businesses based on the open Internet, emphasizing the independence of services from physical networks.

With the development of OTT, almost every household will have at least one piece of equipment that can realize OTT services, such as a TV.

overview

In a first aspect, the present disclosure provides a method for establishing an advertisement preference model, which includes:

Analyzing the advertising exposure data and the insertion order data to determine the completion rate and bounce rate of the advertisement corresponding to the insertion order identifier; the advertisement exposure data is associated with the insertion order data through the insertion order identifier; and

An advertisement preference model is established based on the insertion order identifier, the completion rate and the bounce rate.

In some embodiments, the analysis of the advertisement exposure data and the insertion order data to determine the completion rate and bounce rate of the advertisement corresponding to the insertion order identifier includes:

Determining the ratio of the number of advertisements whose exposure duration exceeds the first preset duration to the total number of advertisements as the completion rate of the advertisement corresponding to the insertion order identifier;

Determining the ratio of the number of advertisements whose exposure duration does not exceed the second preset duration to the total number of advertisements as the bounce rate of the advertisement corresponding to the insertion order identifier; and

The first preset duration is longer than the second preset duration.

In some embodiments, the advertisement exposure data includes the MAC address of the advertisement playback device,

The analysis of the advertisement exposure data and the advertisement order data to determine the completion rate and bounce rate of the advertisement corresponding to the advertisement order identifier includes:

In the advertisement played by the advertisement playback device, there is an advertisement exposure duration exceeding the first preset duration, and the MAC address of the advertisement playback device is determined to be the first target MAC address, and the number of the first target MAC address is compared with the first target MAC address. The ratio of the quantity of all MAC addresses in the advertisement exposure data is determined as the completion rate of the advertisement corresponding to the advertisement order identifier;

In the advertisement played by the advertisement playback device, there is an advertisement exposure duration that does not exceed the second preset duration, and it is determined that the MAC address of the advertisement playback device is the second target MAC address, and the number of the second target MAC address is compared with the The ratio of the numbers of all MAC addresses in the advertisement exposure data is determined as the bounce rate of the advertisement corresponding to the insertion order identifier; and

The first preset duration is longer than the second preset duration.

determining the average duration of advertisement exposure duration corresponding to the MAC address;

If the average duration exceeds the first preset duration, determine that the MAC address is the first target MAC address, and compare the number of the first target MAC address in the advertisement exposure data with all The ratio of the number of MAC addresses is determined as the completion rate of the advertisement corresponding to the insertion order identifier;

If the average duration does not exceed the second preset duration, then determine that the MAC address is the second target MAC address, and compare the number of the second target MAC address in the advertisement exposure data with that in the advertisement exposure data The ratio of the number of all MAC addresses is determined as the bounce rate of the advertisement corresponding to the insertion order identifier; and

The first preset duration is longer than the second preset duration.

In some embodiments, the establishment of an advertising preference model based on the insertion order identifier, the completion rate and the bounce rate includes:

Determine a first judgment value and a second judgment value corresponding to the insertion order identifier according to the completion rate and bounce rate of the advertisement corresponding to the insertion order identifier; and

The advertisement preference model is established based on the first judgment value and the second judgment value.

In some embodiments, the determination of the first judgment value and the second judgment value corresponding to the insertion order identifier according to the completion rate and bounce rate of the advertisement corresponding to the insertion order identifier includes:

Determine the ratio of the completion rate to the bounce rate of the advertisement corresponding to the insertion order identifier, and determine the difference between the ratio and a preset ratio as the first judgment value corresponding to the insertion order identifier; and

The sum of the completion rate and the bounce rate of the advertisement corresponding to the insertion order identifier is determined as the second judgment value corresponding to the insertion order identifier.

In some embodiments, the establishment of the advertisement preference model based on the first judgment value and the second judgment value includes:

If the first judgment value is greater than the first preset value, then it is determined that the advertisement order identifier corresponds to the advertisement content as the user's favorite content;

Or, the first judgment value is less than or equal to the first preset value and greater than or equal to a second preset value, and the second judgment value is greater than or equal to a third preset value, then the advertising order is determined Identify the corresponding advertising content as polarized content;

Or, the first judgment value is less than or equal to the first preset value and greater than or equal to a second preset value, and the second judgment value is less than the third preset value and greater than or equal to a fourth preset value, it is determined that the advertising content corresponding to the insertion order identifier is general content;

Or, if the first judgment value is smaller than the second preset value, it is determined that the advertising content corresponding to the advertising order identifier is disliked by the user.

In a second aspect, the present disclosure provides a device for establishing an advertisement preference model, and the device for establishing an advertisement preference model includes:

The determination unit is configured to analyze the advertisement exposure data and the insertion order data, and determine the completion rate and bounce rate of the advertisement corresponding to the insertion order identifier; the advertisement exposure data and the insertion order data are associated through the insertion order identifier; and

The establishment unit is configured to establish an advertisement preference model based on the insertion order identifier, the completion rate and the bounce rate.

In a third aspect, the present disclosure provides an electronic device, which includes a processor, a communication interface, a memory, and a communication bus, wherein, the processor, the communication interface, and the memory complete mutual communication through the communication bus;

a memory configured to store a computer program;

The processor is configured to implement the method for establishing an advertising preference model described in the present disclosure when executing the program stored in the memory.

In a fourth aspect, the present disclosure provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method for establishing an advertisement preference model as described in the present disclosure is implemented.

In some implementations, the method for establishing an advertisement preference model provided by the embodiments of the present disclosure analyzes the advertisement exposure data and the advertisement order data associated with the advertisement order identifier, and determines the completion of the broadcast of the advertisement corresponding to the advertisement order identifier. rate and bounce rate, and based on the completion rate and bounce rate, an advertisement preference model is established to determine whether the user likes the advertisement corresponding to any insertion order identifier through the advertisement preference model.

Brief description of the drawings

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

In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, In other words, other drawings can also be obtained from these drawings without paying creative labor.

FIG. 1 is a schematic flowchart of a method for establishing an advertisement preference model provided by an embodiment of the present disclosure;

FIG. 2 is a schematic diagram of the association between advertising exposure data and advertising order data provided by an embodiment of the present disclosure through an advertising order identifier;

FIG. 3 is a schematic diagram of a modeling process provided by an embodiment of the present disclosure;

FIG. 4 is a schematic diagram of a device for establishing an advertisement preference model provided by an embodiment of the present disclosure; and

Fig. 5 is a schematic diagram of an electronic device provided by an embodiment of the present disclosure.

detail

In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments It is a part of embodiments of the present disclosure, but not all embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present disclosure.

This disclosure provides a method for establishing an advertisement preference model, which is applied to a processor. The processor can be located in a device that can realize OTT services, such as an advertisement playback device (television, etc.), and can also be located in a device that can communicate with the advertisement playback device. other devices, such as servers. As shown in Figure 1, the method for establishing an advertisement preference model includes steps 101-102 as follows:

101. Analyze the advertisement exposure data and the insertion order data, and determine the completion rate and bounce rate of the advertisement corresponding to the insertion order identifier; and

102. Establish an advertisement preference model based on the IO ID, completion rate, and bounce rate.

In some embodiments, the original log data is generated according to the triggering of the embedding event, and the original log data includes advertisement exposure log data (that is, the above advertisement exposure data) and insertion order data.

In some embodiments, taking the equipment capable of implementing OTT services as television equipment as an example, as shown in Table 1 below, the advertisement exposure data (i.e. ad_log_data) includes fields such as logID, mac, ad_schedule_space_no, b_time, and ad_order_no. The names (that is, the field names) are log ID, TV device media access control address (media access control address, MAC), advertising slot ID, advertisement exposure duration, and insertion order ID, etc. Among them, the types of fields such as logID, mac, ad_schedule_space_no, and ad_order_no are character strings, and the types of fields such as b_time are numeric values, and the unit of this field is seconds. Among them, the identification is ID (identity document).

Table 1

字段field	字段名field name	类型type	说明illustrate
logIDlogID	日志IDlog ID	字符串string	the
macmac	电视设备MACTV equipment MAC	字符串string	the
ad_schedule_space_noad_schedule_space_no	广告位IDAd slot ID	字符串string	the
b_timeb_time	广告曝光时长Ad exposure time	数值value	单位：秒Unit: second
ad_order_noad_order_no	广告订单IDinsertion order ID	字符串string	the

Table 2

In some embodiments, as shown in Table 2 above, the insertion order data (that is, ad_order_data) includes fields such as ad_order_n, ad_schedule_space_no, ad_schedule_media_duration, ad_order_begintime, and ad_order_endtime, and the names of these fields (that is, field names) are the insertion order identifier, advertisement bit identifier, creative duration, insertion order delivery start time, insertion order delivery end time, etc. The types of fields such as ad_order_no and ad_schedule_space_no are strings, the types of fields such as ad_schedule_media_duration are numeric values, and the unit of this field is seconds, and the types of fields such as ad_order_begintime and ad_order_endtime are dates.

It should be noted that the duration of the above-mentioned creative material is the duration of the complete playback of the advertisement. Ad exposure duration refers to the duration of ad playback.

Wherein, the advertisement exposure data is associated with the insertion order data through the insertion order identifier. As shown in FIG. 2 , the advertisement exposure data table (table: ad_log_data) and the insertion order data (table: ad_order_data) are associated through the insertion order identification field (field: ad_log_data).

In some embodiments, the ratio of the number of advertisements whose exposure duration exceeds the first preset duration to the total number of advertisements is determined as the completion rate of the advertisement corresponding to the insertion order identifier. And determine the ratio of the number of advertisements whose exposure duration of the advertisement does not exceed the second preset duration to the total number of advertisements as the bounce rate of the advertisement corresponding to the insertion order identifier.

That is to say, if the advertisement exposure duration exceeds the first preset duration, it is determined that the advertisement has been completely played. At this time, the completion rate of the advertisement can be determined according to the number of advertisements whose advertisement exposure duration exceeds the first preset duration.

Since the effective content in the advertisement may only occupy a period of time before the duration of the corresponding creative, such as the first 5s, at this time, if the playing duration of the advertisement reaches, for example, 5s, it is considered that the advertisement has been played completely. That is, in a possible implementation manner, the first preset duration may be shorter than the duration of the creative.

In some embodiments, the first preset duration is 80% of the duration of the creative.

In order to ensure the accuracy of the completion rate, in another possible implementation manner, it may be determined that the first preset duration is greater than or equal to the duration of the creative.

Generally, if the advertisement is not finished playing, the user chooses to jump out to stop watching the advertisement. At this time, the exposure duration of the advertisement is shorter than the duration of the creative, that is to say, the second preset duration is shorter than the duration of the creative. Moreover, generally, the effective content of the advertisement cannot be played within the second preset duration, that is to say, the second preset duration is shorter than the first preset duration. Therefore, if the advertisement exposure duration is less than the second preset duration, it is determined that the user jumps out of the advertisement, and the bounce rate of the advertisement can be determined according to the number of advertisements whose advertisement exposure duration is shorter than the second preset duration.

In some embodiments, the second preset duration is 10% of the duration of the creative.

Wherein, the first preset duration is longer than the second preset duration. It should be noted that both the first preset duration and the second preset duration may be predetermined, or may be determined according to actual working conditions.

In some embodiments, the total number of advertisements corresponding to the insertion order identifier is 20, the number of advertisements whose exposure duration exceeds the first preset duration is 10, and the number of advertisements whose exposure duration does not exceed the second preset duration for 5. At this time, the completion rate of the advertisement corresponding to the insertion order identifier is 0.5, and the bounce rate of the advertisement corresponding to the insertion order identifier is 0.25.

In some embodiments, the ad exposure data includes the MAC address of the ad playing device. At this time, there is an advertisement exposure duration in the advertisement played by the advertisement playback device that exceeds the first preset duration, determine that the MAC address of the advertisement playback device is the first target MAC address, and compare the number of the first target MAC address with the advertisement exposure data. The ratio of the numbers of all MAC addresses is determined as the completion rate of the advertisement corresponding to the insertion order identifier. In addition, if the advertisement played by the advertisement playback device has an advertisement exposure duration that does not exceed the second preset duration, determine that the MAC address of the advertisement playback device is the second target MAC address, and compare the number of the second target MAC address with the advertisement exposure data. The ratio of the numbers of all MAC addresses is determined as the bounce rate of the advertisement corresponding to the insertion order identifier.

For the introduction of the first preset duration and the second preset duration, reference may be made to the above content, and details are not repeated here.

In some embodiments, there are 4 MAC addresses of the advertisement playback devices involved in the advertisement exposure data corresponding to the insertion order identifier a, namely MAC1, MAC2, MAC3 and MAC4, that is, the number of advertisement playback devices is 4 indivual. At this time, the advertisement exposure durations corresponding to MAC1 and MAC4 in the advertisement playback data do not exceed the first preset duration, and among the advertisement exposure durations corresponding to MAC2 and MAC3, there is an advertisement exposure duration exceeding the first preset duration. There is an advertisement exposure duration that does not exceed the second preset duration, and there is no advertisement exposure duration that does not exceed the second preset duration in the MAC4. At this time, the number of the first target MAC address is 2, and the number of the second target MAC address is 1. The completion rate of the advertisement corresponding to the insertion order identifier a is 0.5, and the bounce rate of the advertisement corresponding to the insertion order identifier a is 0.25.

In some embodiments, the ad exposure data includes the MAC address of the ad playing device. The advertisement exposure duration corresponding to the advertisement played by the advertisement playback device does not exceed the second preset duration, determine that the MAC address of the advertisement playback device is the second target MAC address, and compare the number of the second target MAC address with all the advertisement exposure data. The ratio of the number of MAC addresses is determined as the bounce rate of the advertisement corresponding to the insertion order identifier. In addition, the advertisement exposure durations corresponding to the advertisements played by the advertisement playback device all exceed the first preset duration, determine that the MAC address of the advertisement playback device is the first target MAC address, and compare the number of the first target MAC address with the advertisement exposure data. The ratio of the numbers of all MAC addresses is determined as the completion rate of the advertisement corresponding to the insertion order identifier.

It should be noted that the above two ways of determining the first target MAC address and the above two ways of determining the second target MAC address can be freely combined, and are not specifically limited here.

In some embodiments, the ad exposure data includes the MAC address of the ad playing device.

First determine the average duration of advertisement exposure corresponding to the MAC address. Subsequently, the completion rate of the advertisement corresponding to the insertion order identifier is determined according to the average duration corresponding to the MAC address. Wherein, the insertion order identifier is the insertion order identifier corresponding to the advertisement exposure data described below.

In some embodiments, if the average duration exceeds the first preset duration, the MAC address is determined to be the first target MAC address, and the number of the first target MAC address in the advertisement exposure data is compared with the number of all MAC addresses in the advertisement exposure data The ratio of the quantity is determined as the completion rate of the advertisement corresponding to the insertion order identifier. If the average duration does not exceed the second preset duration, the MAC address is determined to be the second target MAC address, and the ratio of the quantity of the second target MAC address in the advertisement exposure data to the quantity of all MAC addresses in the advertisement exposure data is determined as The bounce rate of the ad for the insertion order ID.

In some embodiments, there are 4 MAC addresses of the advertisement playback devices involved in the advertisement exposure data corresponding to the insertion order identifier a, namely MAC1, MAC2, MAC3 and MAC4, that is, the number of advertisement playback devices is 4 indivual. At this time, the average duration of advertisement exposure corresponding to MAC1 and MAC4 in the advertisement playback data exceeds the first preset duration, and the average duration of advertisement exposure corresponding to MAC2 and MAC3 does not exceed the second preset duration. At this time, the number of the first target MAC address is 2, and the number of the second target MAC address is 2. The completion rate of the advertisement corresponding to the insertion order identifier a is 0.5, and the bounce rate of the advertisement corresponding to the insertion order identifier a is 0.5.

It should be noted that, compared to the scheme of determining the completion rate and bounce rate of the advertisement corresponding to the insertion order identifier determined by the MAC address, the completion rate and bounce rate of the advertisement corresponding to the insertion order identifier determined by the MAC address may be lower. It is more accurate, and it is convenient to establish a more accurate advertisement preference model, so that it can be more accurately determined whether the user likes the advertisement content corresponding to any insertion order identifier according to the advertisement preference model.

In some embodiments, the first judgment value and the second judgment value corresponding to the insertion order identifier are determined according to the completion rate and the bounce rate of the advertisement corresponding to the insertion order identifier. Subsequently, an advertisement preference model is established based on the first judgment value and the second judgment value.

In some embodiments, the dimensions (or basic fields) used to establish the advertisement preference model may be as shown in Table 3 below, where T is the creative duration of the advertisement corresponding to the insertion order identifier. At this point, f (completion rate) = count((average duration/creative duration)>0.8)/count(*), g(bounce rate)=count((average duration/creative duration)<0.1)/count (*). Among them, count((average duration/creative duration)>0.8) indicates the number of MAC addresses whose ratio of average duration to creative duration is greater than 80%, and count((average duration/creative duration)<0.1) indicates the ratio of average duration to creative duration The number of MAC addresses whose duration ratio of the creative is less than 10%, and count(*) indicates the total number of MAC addresses. That is, the average durations shown in Table 3 are used to determine completion and bounce rates.

table 3

In some embodiments, the ratio of the completion rate to the bounce rate of the advertisement corresponding to the insertion order identifier is determined, and the difference between the ratio and the preset ratio is determined as the first judgment value corresponding to the insertion order identifier. In addition, the sum of the completion rate and the bounce rate of the advertisement corresponding to the insertion order identifier is determined as the second judgment value corresponding to the insertion order identifier. Wherein, the preset ratio may be predetermined or determined according to actual working conditions.

In certain embodiments, k=f/g-1, s=f+g. Among them, k is the first judgment value, s is the second judgment value, f is the completion rate, g is the bounce rate, and the preset ratio is 1.

In some embodiments, if the first judgment value is greater than the first preset value, then it is determined that the advertising order identifier corresponds to the user's favorite content; or, the first judgment value is less than or equal to the first preset value, and greater than or equal to the second preset value, and the second judgment value is greater than or equal to the third preset value, then it is determined that the advertising content corresponding to the insertion order logo is polarized content; or, the first judgment value is less than or equal to the first preset value , and greater than or equal to the second preset value, and the second judgment value is less than the third preset value, and greater than or equal to the fourth preset value, then it is determined that the advertising content corresponding to the insertion order identifier is general content; or, the first judgment If the value is less than the second preset value, then it is determined that the advertisement content corresponding to the insertion order identifier is disliked (or disliked) by the user.

Wherein, the first preset value, the second preset value, the third preset value and the fourth preset value may all be predetermined or determined according to actual working conditions. The third preset value may be the same as or different from the first preset value. The first preset value is greater than the second preset value, and the third preset value is greater than the fourth preset value.

It should be noted that the above-mentioned polarized content refers to the content that the user may or may not like (or sometimes like and sometimes dislike), and the general content refers to the content that the user neither likes nor dislikes.

In some implementations, taking the advertisement corresponding to the insertion order identifier a as a startup advertisement as an example, k=f/g-1, s=f+g. Among them, k is the first judgment value, s is the second judgment value, f is the completion rate, g is the bounce rate, and the preset ratio is 1. If the value of k is (0.5, +∞), it is determined that the advertising content corresponding to the insertion order identifier a is the user's favorite content; if the value of k is [-0.5, 0.5], and the value of s is [0.5 , +∞), it is determined that the advertising content corresponding to the insertion order ID a is polarized content; if the value of k is [-0.5, 0.5], and the value of s is [0, 0.5), then the insertion order ID is determined The advertisement content corresponding to a is general content; if the value of k is (-∞, -0.5), it is determined that the advertisement order identifier a corresponds to the advertisement content that is disliked by the user. That is to say, the first preset value is 0.5, the second preset value is -0.5, the third preset value is 0.5, and the fourth preset value is -0.5.

In some embodiments, the preferred content and the disliked content can be further divided, for example, the preferred content is divided into highly preferred content and relatively preferred content, for example, the disliked content is divided into highly disliked content and less preferred content.

In some embodiments, if the first judgment value is greater than the first preset value and smaller than the fifth preset value, then it is determined that the advertising content corresponding to the insertion order identifier is the user's preferred content; or the first judgment value is greater than or equal to the fifth preset value. five preset values, then it is determined that the advertisement content corresponding to the insertion order identifier is the user’s highly preferred content; or the first judgment value is less than the second preset value and greater than the sixth preset value, then it is determined that the advertisement content corresponding to the insertion order identifier is The content that the user dislikes less; or the first judgment value is less than the sixth preset value, then it is determined that the advertising content corresponding to the insertion order identifier is the content that is highly disliked by the user. For other solutions for determining whether the advertisement content corresponding to the insertion order identifier is polarized content or general content, please refer to the above content, and details will not be described here.

Wherein, the fifth preset value is greater than the first preset value, and the sixth preset value is smaller than the second preset value. Both the fifth preset value and the sixth preset value can be predetermined, or can be determined according to actual working conditions. For the introduction of the first preset value to the fourth preset value, reference may be made to the above content, and details are not repeated here.

In some implementations, taking the advertisement corresponding to the insertion order identifier a as a startup advertisement as an example, k=f/g-1, s=f+g. Among them, k is the first judgment value, s is the second judgment value, f is the completion rate, g is the bounce rate, and the preset ratio is 1. If the value of k is [2, +∞), it is determined that the advertising content corresponding to the insertion order identifier a is the user’s highly preferred content; if the value of k is (0.5, 2), then it is determined that the advertisement content corresponding to the insertion order identifier a The advertisement content is the user's preferred content; if the value of k is [-0.5, 0.5], and the value of s is [0.5, +∞), it is determined that the advertisement content corresponding to the insertion order identifier a is polarized content; If the value of k is [-0.5, 0.5], and the value of s is [0, 0.5), it is determined that the advertising content corresponding to the insertion order identifier a is general content; if the value of k is (-2, - 0.5), then it is determined that the advertising order ID a corresponds to the content that the user dislikes; if the value of k is (-∞, -2], then it is determined that the advertising order ID a corresponds to the user’s advertising content High dislike content. That is to say, the first default value is 0.5, the second default value is -0.5, the third default value is 0.5, the fourth default value is -0.5, and the fifth default value is 2 , the sixth default value is -2.

In some embodiments, as shown in FIG. 3 , the modeling process includes three steps: data collection, data cleaning calculation, and model construction. Data collection includes collecting advertisement exposure data (or advertisement exposure logs) and collecting advertisement order data, among which the advertisement exposure data includes advertisement completion data and advertisement jump-out data. The data cleaning calculation means to process the advertisement exposure data and the insertion order data according to the duration of the creative material, the duration of the advertisement exposure, etc. The model construction includes calculating the model classification index based on the above-mentioned cleaned data. The model classification index includes the average exposure duration ( That is, the above-mentioned average duration), completion rate and bounce rate, etc.

It should be noted that, through the above process, the advertisement exposure data and insertion order data associated with the insertion order identifier are analyzed to determine the completion rate and bounce rate of the advertisement corresponding to the insertion order identifier, so that according to the completion rate and the bounce rate, an advertisement preference model is established, so as to determine whether the user likes the advertisement corresponding to any insertion order identifier through the advertisement preference model.

Based on the same idea, the present disclosure also provides a device 400 for establishing an advertising preference model. For the implementation of the device, please refer to the description of the method embodiment, and the repetition will not be repeated. As shown in Figure 4, the device mainly includes:

The determination unit 401 is configured to analyze the advertisement exposure data and the insertion order data, and determine the completion rate and bounce rate of the advertisement corresponding to the insertion order identifier; the advertisement exposure data and the advertisement order data are associated through the insertion order identifier; as well as

The establishing unit 402 is configured to establish an advertisement preference model based on the insertion order identifier, the completion rate and the bounce rate.

Based on the same idea, the present disclosure also provides an electronic device 500. As shown in FIG. Complete mutual communication through the communication bus 504,

memory 503 configured to store computer programs;

In some embodiments, the processor 501 is configured to implement the method for establishing an advertisement preference model provided in the present disclosure when executing the program stored in the memory 503 .

The present disclosure also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the method for establishing an advertising preference model provided by the present disclosure is implemented.

It should be noted that in this article, relative terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply these No such actual relationship or order exists between entities or operations. Furthermore, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus comprising a set of elements includes not only those elements, but also includes elements not expressly listed. other elements of or also include elements inherent in such a process, method, article, or device. Without further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising said element.

The above descriptions are only specific implementation manners of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not 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

A method for establishing an advertisement preference model, wherein the method includes:

Analyzing the advertising exposure data and the insertion order data to determine the completion rate and bounce rate of the advertisement corresponding to the insertion order identifier; the advertisement exposure data is associated with the insertion order data through the insertion order identifier; and

An advertisement preference model is established based on the insertion order identifier, the completion rate and the bounce rate.
The method for establishing an advertisement preference model according to claim 1, wherein said analyzing the advertisement exposure data and the advertisement order data to determine the completion rate and the bounce rate of the advertisement corresponding to the advertisement order identifier comprises:

Determining the ratio of the number of advertisements whose exposure duration exceeds the first preset duration to the total number of advertisements as the completion rate of the advertisement corresponding to the insertion order identifier;

Determining the ratio of the number of advertisements whose exposure duration does not exceed the second preset duration to the total number of advertisements as the bounce rate of the advertisement corresponding to the insertion order identifier; and

The first preset duration is longer than the second preset duration.
The method for establishing an advertisement preference model according to claim 1 or 2, wherein the advertisement exposure data includes the MAC address of the advertisement playback device,

The analysis of the advertisement exposure data and the advertisement order data to determine the completion rate and bounce rate of the advertisement corresponding to the advertisement order identifier includes:

In the advertisement played by the advertisement playback device, there is an advertisement exposure duration exceeding the first preset duration, and the MAC address of the advertisement playback device is determined to be the first target MAC address, and the number of the first target MAC address is compared with the first target MAC address. The ratio of the quantity of all MAC addresses in the advertisement exposure data is determined as the completion rate of the advertisement corresponding to the advertisement order identifier;

In the advertisement played by the advertisement playback device, there is an advertisement exposure duration that does not exceed the second preset duration, and it is determined that the MAC address of the advertisement playback device is the second target MAC address, and the number of the second target MAC address is compared with the The ratio of the numbers of all MAC addresses in the advertisement exposure data is determined as the bounce rate of the advertisement corresponding to the insertion order identifier; and

The first preset duration is longer than the second preset duration.
The method for establishing an advertisement preference model according to any one of claims 1 to 3, wherein the advertisement exposure data includes the MAC address of the advertisement playback device,

The analysis of the advertisement exposure data and the advertisement order data to determine the completion rate and bounce rate of the advertisement corresponding to the advertisement order identifier includes:

determining the average duration of advertisement exposure duration corresponding to the MAC address;

If the average duration exceeds the first preset duration, determine that the MAC address is the first target MAC address, and compare the number of the first target MAC address in the advertisement exposure data with all The ratio of the number of MAC addresses is determined as the completion rate of the advertisement corresponding to the insertion order identifier;

If the average duration does not exceed the second preset duration, then determine that the MAC address is the second target MAC address, and compare the number of the second target MAC address in the advertisement exposure data with that in the advertisement exposure data The ratio of the number of all MAC addresses is determined as the bounce rate of the advertisement corresponding to the insertion order identifier; and

The first preset duration is longer than the second preset duration.
The method for establishing an advertisement preference model according to any one of claims 1 to 4, wherein said establishment of an advertisement preference model based on said advertisement order identifier, said completion rate and said bounce rate includes:

Determine a first judgment value and a second judgment value corresponding to the insertion order identifier according to the completion rate and bounce rate of the advertisement corresponding to the insertion order identifier; and

The advertisement preference model is established based on the first judgment value and the second judgment value.
The method for establishing an advertisement preference model according to claim 5, wherein, according to the completion rate and bounce rate of the advertisement corresponding to the advertisement order identifier, the first judgment value and the second judgment value corresponding to the advertisement order identifier are determined. Judgment value, including:

Determine the ratio of the completion rate to the bounce rate of the advertisement corresponding to the insertion order identifier, and determine the difference between the ratio and a preset ratio as the first judgment value corresponding to the insertion order identifier; and

The sum of the completion rate and the bounce rate of the advertisement corresponding to the insertion order identifier is determined as the second judgment value corresponding to the insertion order identifier.
The method for establishing an advertisement preference model according to claim 5 or 6, wherein said establishment of said advertisement preference model based on said first judgment value and said second judgment value comprises:

If the first judgment value is greater than the first preset value, then it is determined that the advertisement order identifier corresponds to the advertisement content as the user's favorite content;

Or, the first judgment value is less than or equal to the first preset value and greater than or equal to a second preset value, and the second judgment value is greater than or equal to a third preset value, then the advertising order is determined Identify the corresponding advertising content as polarized content;

Or, the first judgment value is less than or equal to the first preset value and greater than or equal to a second preset value, and the second judgment value is less than the third preset value and greater than or equal to a fourth preset value, it is determined that the advertising content corresponding to the insertion order identifier is general content;

Or, if the first judgment value is smaller than the second preset value, it is determined that the advertising content corresponding to the advertising order identifier is disliked by the user.
A device for establishing an advertisement preference model, wherein the device includes:

The determination unit is configured to analyze the advertisement exposure data and the insertion order data, and determine the completion rate and bounce rate of the advertisement corresponding to the insertion order identifier; the advertisement exposure data and the insertion order data are associated through the insertion order identifier; and

The establishment unit is configured to establish an advertisement preference model based on the insertion order identifier, the completion rate and the bounce rate.
An electronic device, comprising: a processor, a memory, and a communication bus, wherein the processor and the memory complete mutual communication through the communication bus;

the memory configured to store a computer program;

The processor is configured to execute the program stored in the memory, so as to implement the method for establishing an advertising preference model according to any one of claims 1 to 7.
A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the method for establishing an advertising preference model according to any one of claims 1 to 7 is implemented.