An intelligent advertisement delivery management method, device, equipment and storage medium

Abstract

The application discloses an intelligent advertisement putting management method and device, equipment and storage medium, relates to the intelligent recommendation management technical field, and in one aspect, the application carries out data analysis on the browsing data generated by the short video platform before the user portrait label of any user terminal is newly added, extracts the time spent by the user terminal in preliminarily establishing interest in the related short video corresponding to the newly added user portrait label, and the time is also the time spent by the user terminal in preliminarily establishing interest in the short video content not belonging to the big data label of the user terminal; in another aspect, the time spent by the user terminal in preliminarily establishing interest in the short video advertisement on the short video platform is analyzed by analyzing the commodity transaction record generated by the user terminal in preliminarily establishing interest in the short video advertisement; the two kinds of time extracted are matched, so that the effective delivery of the short video advertisement to the user terminal is improved, and the adhesion of the short video platform and the user terminal is promoted.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent recommendation management, and particularly relates to an intelligent advertisement putting management method, device, equipment and storage medium. BACKGROUND

[0002] The advertisement put in the form of short video is short video advertisement, which generally appears in various social, short video and news information apps. Through several minutes or even only a few seconds of short video, the user can be pushed at a high frequency, including knowledge sharing, creative advertisement, social hot spot, popular fashion and other style themes. With the development and popularity of short video in recent years, short video advertisement emerges as the times require, whether in form or in content, short video advertisement is completely new compared with traditional advertisement mode.

[0003] Intelligent putting is a kind of efficient and accurate advertisement putting method in the marketing field. It uses artificial intelligence technology and data analysis method to accurately display the advertisement to the target audience group according to the characteristics, interests and behaviors of the user and other information; the intelligent putting system understands the interests, purchase behaviors and preferences of the user by analyzing a large amount of data such as the user's browsing record, search history, social media behavior and other information. Then, combined with machine learning and artificial intelligence technology, the system can display personalized advertisements to potential customers at the right time and in the right place. SUMMARY

[0004] The present application aims to provide an intelligent advertisement putting management method, device, equipment and storage medium to solve the problems in the prior art.

[0005] To achieve the above-mentioned purpose, the present application provides the following technical scheme: an intelligent advertisement putting management method, the method comprising:

[0006] Step S1: monitoring the short video platform by collecting the browsing data of each user terminal, and monitoring the change of the user portrait label generated for each user terminal;

[0007] Step S2: whenever a new user portrait label is captured on any user terminal, combing the short video sequence browsed in the process of generating a new user portrait label on any user terminal, and classifying each short video contained in the short video sequence according to the difference of the corresponding user portrait label;

[0008] Step S3: according to the distribution of short videos of different categories in the short video sequence, extracting a plurality of target video sequences, and evaluating the browsing degree value of any target video sequence on the user terminal;

[0009] Step S4: In the short video sequence, analyze the changing trend of the browsing degree value presented by the user terminal for different target video sequences, and extract the characteristic browsing attribute value of the user terminal;

[0010] Step S5: Analyze the product transaction data generated by users browsing short video ads on the short video platform, and analyze the duration of the effect of any short video ad that can prompt users to make a transaction.

[0011] Step S6: By matching the user's browsing attribute values ​​with the duration of the short video ad effect, intelligent ad delivery is performed on user terminals that have captured new user profile tags.

[0012] Preferably, step S2 includes:

[0013] Step S2-1: When the user profile tag set Q(T0) generated by the short video platform for a certain user terminal up to timestamp T0 is detected, and the tag set Q(T0) up to timestamp T0 is compared with the tag set Q(T0) generated by the short video platform for a certain user terminal up to timestamp T0, the user profile tag set Q(T0) up to timestamp T0 is compared with the user profile tag set Q(T0) up to timestamp T0 up to timestamp T e The user profile tag set Q(T) generated at that time e ), satisfying Sum(F)=1, F=Q(T) e )-[Q(T e )∩Q(T0)], and β≧T e When -T0>0, extract the time range [T0,T] of a certain user terminal. e The short video sequence D browsed within the set; where β is the average time difference between the pre-set user profile tag updates, and Sum(F) represents the total number of user profile tags contained in the set F;

[0014] This means that the deadline is timestamp T. e The user profile tag set generated for the user client at time T0 has an additional user profile tag compared to the user profile tag set generated for the user client up to timestamp T0. Since the above relationship is satisfied between the two timestamps, it means that the time interval between the two timestamps satisfies the time difference for the user profile tag update.

[0015] Step S2-2: Set the one and only user profile tag contained in set F as the target tag, extract the short video corresponding to the target tag from the short video sequence D and set it as the first feature video, and set the other short videos as the second feature videos.

[0016] In real-world scenarios, short video platforms typically first push relevant short videos to a user's device using a user profile tag set Q(T0) as a reference. Based on the actual browsing data generated by the user's device, the user profile tags for that user's device are adjusted. Specifically, a new user profile tag, the target tag, is added to the user profile tag set Q(T0).

[0017] Preferably, step S3 comprises:

[0018] Step S3-1: obtaining the video duration T of each short video in the short video sequence D L , extracting the actual browsing duration T of each short video by a certain user terminal r ; calculating the browsing degree value β = T r / T L of each short video by a certain user terminal

[0019] Step S3-2: extracting the first characteristic video arranged individually and the first characteristic video arranged continuously by M in the short video sequence D as the first target video sequence; extracting the second characteristic video arranged individually and the second characteristic video arranged continuously by M in the short video sequence D as the second target video sequence; wherein M≧2;

[0020] Step S3-3: evaluating the browsing index α = [β 1 + β 2 +... + β n ] / n of each first target video sequence or second target video sequence in the short video sequence D by a certain user terminal, wherein β 1 , β 2 ,..., β n represent the browsing degree value of the 1st, 2nd,..., nth short video in each first target video sequence or second target video sequence by a certain user terminal.

[0021] Preferably, step S4 comprises:

[0022] Step S4-1: sequentially accumulating the browsing index of each first target video sequence according to the arrangement order of the first target video sequence and the second target video sequence in the short video sequence D, and simultaneously sequentially accumulating the browsing index of each second target video sequence;

[0023] Step S4-2: when the total browsing index δ1 obtained by accumulating the browsing index of the 1st to ith first target video sequence and the total browsing index δ2 obtained by accumulating the browsing index of the 1st to jth second target video sequence satisfy δ2-δ1<θ, extracting all the first characteristic videos contained in the 1st to ith first target video sequence as target short videos, obtaining the average actual browsing duration Tg of all target short videos by a certain user terminal, and setting the average actual browsing duration Tg as the characteristic browsing attribute value of a certain user terminal; wherein i≦R1, R1 is the total number of first target video sequences contained in the short video sequence D; j≦R2, R2 is the total number of second target video sequences contained in the short video sequence D; wherein θ is the index deviation threshold.

[0024] Preferably, step S5 comprises:

[0025] Step S5-1: From the backstage end of the short video platform, for any short video advertisement, collect all user-side generated transaction records of goods through browsing any short video advertisement and according to the corresponding jump of the goods link, and set the transaction record of goods as the effect record of any short video advertisement;

[0026] Step S5-2: For each effect record of any short video advertisement, capture the actual browsing duration of the corresponding user side to any short video advertisement before the corresponding user side establishes each effect record in the short video platform, set the actual browsing duration as the effect duration of any short video advertisement corresponding to each effect record, and obtain the average effect duration of any short video advertisement corresponding to all effect records;

[0027] In combination with the actual scene, before the corresponding user establishes a certain effect record in the short video platform, the actual browsing duration of the user to the corresponding short video advertisement is basically the duration of the user locking the interest in the corresponding goods in the short video advertisement. From the short video advertisement itself, the product information delivered to the user side in this duration may be the most attractive place in the short video advertisement.

[0028] Preferably, step S6 comprises: if the feature browsing attribute value X extracted from a certain user side with a newly added user portrait label satisfies X >= Y, the average effect duration Y corresponding to a certain short video advertisement, feedback to add a certain short video advertisement to the short video sequence to be put to a certain user.

[0029] In order to better realize the above method, an intelligent advertisement putting management device is also proposed. The device comprises a platform browsing data collection management module, a short video extraction classification module, a browsing degree value evaluation management module, a feature browsing attribute value calculation module, an effect duration extraction management module, and an advertisement intelligent putting management module.

[0030] The platform browsing data collection management module is used to monitor the short video platform by collecting the browsing data of each user side, and the change of the user portrait label generated for each user side;

[0031] The short video extraction classification module is used to comb the short video sequence browsed by any user side in the process of newly added user portrait label when the newly added user portrait label of any user side is captured, and classify each short video contained in the short video sequence according to the difference of the corresponding user portrait label.

[0032] The browsing degree value evaluation management module is configured to extract a plurality of target video sequences according to the distribution of short videos of different categories in the short video sequence, and evaluate the browsing degree value of the user terminal for any target video sequence.

[0033] The characteristic browsing attribute value calculation module is configured to extract a plurality of target video sequences according to the distribution of short videos of different categories in the short video sequence, and evaluate the browsing degree value of the user terminal for any target video sequence.

[0034] The effect duration extraction management module is configured to analyze the change trend of the browsing degree value of the user terminal for different target video sequences in the short video sequence, and extract the characteristic browsing attribute value of the user terminal.

[0035] The advertisement intelligent delivery management module is configured to perform intelligent delivery on the user terminal with the newly added user portrait label by matching the characteristic browsing attribute value of the user terminal with the effect duration of the short video advertisement.

[0036] A storage medium, the storage medium stores computer instructions, the computer instructions are executed by the processor, and the computer instructions can implement any of the intelligent advertisement delivery management methods.

[0037] An intelligent advertisement delivery management device, the device includes a memory and at least one processor, the memory stores computer instructions, and the at least one processor calls the computer instructions in the memory to make the intelligent advertisement delivery management device execute any of the intelligent advertisement delivery management methods.

[0038] Compared with the prior art, the beneficial effects of the present application are: in one aspect, the present application analyzes the browsing data generated by the short video platform before the user terminal generates a new user portrait label, extracts the time spent by the user terminal in establishing interest in the related short video corresponding to the new user portrait label, and the time is also the time spent by the user terminal in establishing interest in the short video content that does not belong to the user's big data label; in another aspect, by analyzing the product transaction records generated by the user terminal when browsing the short video advertisement on the short video platform, the time spent by the short video advertisement to produce advertising effect on the user terminal is analyzed; by matching the two extracted times, the effective delivery of the short video advertisement to the user terminal is improved, and the adhesion of the short video platform and the user terminal is promoted. BRIEF DESCRIPTION OF DRAWINGS

[0039] Fig. 1 The flowchart of the intelligent advertisement delivery management method of the present application;

[0040] Fig. 2 The structure diagram of the intelligent advertisement delivery management device of the present application. Detailed Implementation

[0041] Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0042] Example: Figs. 1-2 As shown, the present invention provides an intelligent advertising delivery management method, the method comprising:

[0043] Step S1: Monitor the changes in user profile tags generated for each user by collecting browsing data from various user terminals on the short video platform;

[0044] Step S2: Whenever a new user profile tag is captured for any user terminal, sort out the short video sequence viewed by any user terminal during the process of the new user profile tag, and classify each short video contained in the short video sequence according to the different corresponding user profile tags.

[0045] Step S2 includes:

[0046] Step S2-1: When the user profile tag set Q(T0) generated by the short video platform for a certain user terminal up to timestamp T0 is detected, and the tag set Q(T0) up to timestamp T0 is compared with the tag set Q(T0) generated by the short video platform for a certain user terminal up to timestamp T0, the user profile tag set Q(T0) up to timestamp T0 is compared with the user profile tag set Q(T0) up to timestamp T0 up to timestamp T e The user profile tag set Q(T) generated at that time e ), satisfying Sum(F)=1, F=Q(T) e )-[Q(T e )∩Q(T0)], and β≧T e When -T0>0, extract the time range [T0,T] of a certain user terminal. e The short video sequence D browsed within the set; where β is the average time difference between the pre-set user profile tag updates, and Sum(F) represents the total number of user profile tags contained in the set F;

[0047] Step S2-2: Set the one and only user profile tag contained in set F as the target tag, extract the short video corresponding to the target tag from the short video sequence D and set it as the first feature video, and set the other short videos as the second feature videos.

[0048] For example, for a user profile tag set Q(T0) = {tag1, tag2, tag3, tag4} generated up to timestamp T0, the tag set up to timestamp T0 is... e The user profile tag set Q(T) generated at that time e The set of user profile tags Q(T0) is defined as {tag1, tag2, tag3, tag4, tag5}, because compared to the user profile tag set Q(T0) generated at timestamp T0, the set of tags at timestamp T0 is...e The user portrait tag set Q(T e ) generated at time T

[0049] Because the short video platform is preferentially pushed to the user end according to the user portrait tag corresponding to the user end when pushing short videos to the user end;

[0050] If the short video sequence browsed by the user end in the time range [T0, T e ] is {short video 1, short video 2, short video 3, short video 4, short video 5, short video 6, short video 7}; wherein, short video 1 corresponds to tag 1, short video 2 corresponds to tag 3, short video 3 corresponds to tag 5, short video 4 corresponds to tag 2, short video 5 corresponds to tag 3, short video 6 corresponds to tag 5, and short video 7 corresponds to tag 5;

[0051] In summary, short video 3, short video 6, and short video 7 are set as the first feature video, and the other short videos are set as the second feature video;

[0052] Step S3: according to the distribution of short videos of different categories in the short video sequence, a plurality of target video sequences are extracted, and the browsing degree value of the user end to any target video sequence is evaluated;

[0053] Step S3 includes:

[0054] Step S3-1: obtain the video duration T L of each short video in the short video sequence D, and extract the actual browsing duration T r of each short video by the user end; calculate the browsing degree value β=T r / T L of each short video by the user end;

[0055] Step S3-2: the first feature video arranged alone and the first feature video arranged continuously M times in the short video sequence D are extracted as the first target video sequence; the second feature video arranged alone and the second feature video arranged continuously M times in the short video sequence D are extracted as the second target video sequence; wherein, M≧2;

[0056] Step S3-3: evaluate the browsing index a of each first target video sequence or second target video sequence in the short video sequence D by the user end, wherein a=[β 1 +β 2 +...+β n ] / n, wherein β 1 , β 2 ,..., β nrespectively represent the browsing degree values of the user terminal to the 1st, 2nd, …, n short videos in each first target video sequence or second target video sequence.

[0057] Step S4: In the short video sequence, the change trend of the browsing degree values presented by the user terminal to different target video sequences is analyzed, and the characteristic browsing attribute value of the user terminal is extracted.

[0058] Step S4 includes:

[0059] Step S4-1: According to the order in which the first target video sequences and the second target video sequences are arranged in the short video sequence D, the browsing indexes of each first target video sequence are sequentially accumulated, and the browsing indexes of each second target video sequence are sequentially accumulated.

[0060] Step S4-2: When the total browsing index δ1 obtained by accumulating the browsing indexes of the 1st to ith first target video sequences and the total browsing index δ2 obtained by accumulating the browsing indexes of the 1st to jth second target video sequences satisfy δ2-δ1<θ, all first characteristic videos contained in the 1st to ith first target video sequences are extracted as target short videos, the average actual browsing time Tg of all target short videos by the user terminal is obtained, and the average actual browsing time Tg is set as the characteristic browsing attribute value of the user terminal; wherein i≦R1, R1 is the total number of first target video sequences contained in the short video sequence D;

[0061] j≦R2, R2 is the total number of second target video sequences contained in the short video sequence D; wherein θ is an index deviation threshold.

[0062] Step S5: Analyzing the transaction data of the user terminal through browsing short video advertisements in the short video platform, and analyzing the effect time of any short video advertisement that can promote the user terminal to generate transaction behavior.

[0063] Step S5 includes:

[0064] Step S5-1: From the background end of the short video platform, for any short video advertisement, collect all transaction records of the user terminal through browsing any short video advertisement and generating corresponding transaction records according to the corresponding jump of the product link, and set the transaction records as the effect records of any short video advertisement.

[0065] Step S5-2: For each effect record of any short video advertisement, capture the actual browsing time of the corresponding user terminal to any short video advertisement before the corresponding user terminal establishes each effect record in the short video platform, and set the actual browsing time as the effect time of any short video advertisement corresponding to each effect record; and obtain the average effect time of any short video advertisement corresponding to all effect records.

[0066] Step S6: Through data matching of the feature browsing attribute value of the user terminal and the effect duration of the short video advertisement, the user terminal with the newly added user portrait label is intelligently put into the short video sequence.

[0067] In step S6, if the feature browsing attribute value X extracted from the user terminal with the newly added user portrait label satisfies X >= Y, the average effect duration Y corresponding to the short video advertisement, the short video advertisement is fed back to the short video sequence to be put into the user.

[0068] To better implement the above method, an intelligent advertisement putting management device is also proposed. The device includes a platform browsing data collection management module, a short video extraction classification module, a browsing degree value evaluation management module, a feature browsing attribute value calculation module, an effect duration extraction management module, and an advertisement intelligent putting management module.

[0069] The platform browsing data collection management module is used to monitor the short video platform by collecting the browsing data of each user terminal, and to monitor the change of the user portrait label generated for each user terminal.

[0070] The short video extraction classification module is used to comb the short video sequence browsed by the user terminal during the process of adding a new user portrait label when capturing the user terminal with the newly added user portrait label, and to classify each short video contained in the short video sequence according to the different corresponding user portrait labels.

[0071] The browsing degree value evaluation management module is used to extract a plurality of target video sequences according to the distribution of short videos of different categories in the short video sequence, and to evaluate the browsing degree value of the user terminal to any target video sequence.

[0072] The feature browsing attribute value calculation module is used to extract a plurality of target video sequences according to the distribution of short videos of different categories in the short video sequence, and to evaluate the browsing degree value of the user terminal to any target video sequence.

[0073] The effect duration extraction management module is used to analyze the change trend of the browsing degree value of the user terminal to different target video sequences in the short video sequence, and to extract the feature browsing attribute value of the user terminal.

[0074] The advertisement intelligent putting management module is used to intelligently put the user terminal with the newly added user portrait label into the short video sequence by matching the feature browsing attribute value of the user terminal with the effect duration of the short video advertisement.

[0075] A storage medium, a computer instruction is stored on the storage medium, the computer instruction is executed by the processor, the computer instruction can realize the intelligent advertisement putting management method.

[0076] An intelligent advertisement putting management device, the device comprises a memory and at least one processor, the computer instruction is stored in the memory, the at least one processor calls the computer instruction in the memory, so that the intelligent advertisement putting management device executes any one of the intelligent advertisement putting management method described above.

[0077] Finally, it should be noted that: the above only for the preferred embodiments of the present application, and not for limiting the present application, although the foregoing embodiments of the present application are described in detail, for the person skilled in the art, it still can be modified, or equivalent replacement is recorded in the technical scheme of the foregoing each embodiment. Any modification, equivalent replacement, improvement, etc. within the spirit and principles of the present application, should be included in the protection scope of the present application.

Claims

1. An intelligent advertisement delivery management method, characterized by: The method comprises: Step S1: monitoring the short video platform by collecting the browsing data of each user terminal, and monitoring the change of the user portrait label generated by each user terminal; Step S2: whenever the occurrence of a new user portrait label is captured for any user terminal, combing the short video sequence browsed by the user terminal in the process of the occurrence of the new user portrait label, and classifying each short video contained in the short video sequence according to the difference of the corresponding user portrait label; Step S3: extracting a plurality of target video sequences according to the distribution of short videos of different categories in the short video sequence, and evaluating the browsing degree value of the user terminal for any target video sequence; Step S4: analyzing the change trend of the browsing degree value of the user terminal for different target video sequences in the short video sequence, and extracting the characteristic browsing attribute value of the user terminal; Step S5: analyzing the commodity transaction data generated by the user terminal by browsing the short video advertisement in the short video platform, and analyzing the effect duration of any short video advertisement that can promote the user terminal to generate a transaction behavior; Step S6: matching the characteristic browsing attribute value of the user terminal with the effect duration of the short video advertisement, and intelligently delivering the user terminal that captures the occurrence of a new user portrait label.

2. The intelligent advertisement delivery management method of claim 1, wherein: The step S2 comprises: Step S2-1: When it is monitored that the short video platform generates a user portrait label set Q(T0) for a user terminal at a time stamp T0, and generates a user portrait label set Q(T e ) at a time stamp T e ), and Sum(F)=1, F=Q(T e )-[Q(T e )∩Q(T0)], and β≥T e -T0>0, extract a short video sequence D browsed by the user terminal in a time range [T0, T e ]; wherein β is a pre-set average interval time difference of user portrait label update, wherein Sum(F) represents the total number of user portrait labels contained in the set F; Step S2-2: setting the only one user portrait label contained in the set F as a target label, extracting the short video corresponding to the target label from the short video sequence D as a first characteristic video, and setting other short videos as second characteristic videos.

3. The intelligent advertisement delivery management method of claim 2, wherein: The step S3 comprises: Step S3-1: Obtain the video duration T of each short video in the short video sequence D L , extract the actual browsing duration T of each short video by the certain user end r ; calculate the browsing degree value β of each short video by the certain user end, β = T r / T L ; Step S3-2: extracting the first target video sequence from the first characteristic video arranged alone and the first characteristic video arranged continuously M times in the short video sequence D; extracting the second target video sequence from the second characteristic video arranged alone and the second characteristic video arranged continuously M times in the short video sequence D; wherein M≥2; Step S3-3: Evaluate the browsing index α=[β] of a user terminal for each first target video sequence or second target video sequence within the short video sequence D. 1 +β 2 +...+β n ] / n, where β 1 β 2 ..., β n These represent the browsing level values ​​of the 1st, 2nd, ..., nth short videos in each first target video sequence or second target video sequence, respectively, from the user's perspective.

4. The intelligent advertisement delivery management method of claim 3, wherein: The step S4 comprises: Step S4-1: according to the order of the arrangement of the first target video sequence and the second target video sequence in the short video sequence D, sequentially accumulating the browsing index of each first target video sequence, and simultaneously sequentially accumulating the browsing index of each second target video sequence; Step S4-2: when the total browsing index δ1 obtained by accumulating the browsing index of the first to i-th first target video sequence and the total browsing index δ2 obtained by accumulating the browsing index of the first to j-th second target video sequence satisfy δ2-δ1<θ, extracting all first characteristic videos contained in the first to i-th first target video sequence as target short videos, obtaining the average actual browsing duration Tg of all target short videos by the user terminal, and setting the average actual browsing duration Tg as the characteristic browsing attribute value of the user terminal; wherein i≤R1, R1 is the total number of first target video sequences contained in the short video sequence D; j≤R2, R2 is the total number of second target video sequences contained in the short video sequence D; wherein θ is an index deviation threshold.

5. The intelligent advertisement delivery management method of claim 4, wherein: The step S5 comprises: Step S5-1: From the backstage end of the short video platform, for any short video advertisement, collecting all user terminals through browsing the arbitrary short video advertisement and generating product transaction records according to the corresponding jump product link, setting the product transaction records as the effect records of the arbitrary short video advertisement; Step S5-2: For each effect record of any short video advertisement, capturing the actual browsing time length of the corresponding user terminal to the arbitrary short video advertisement before the corresponding user terminal establishes each effect record in the short video platform, setting the actual browsing time length as the effect time length of each effect record corresponding to any short video advertisement; obtaining the average effect time length of all effect records corresponding to any short video advertisement.

6. The intelligent advertisement delivery management method of claim 4, wherein: The step S6 comprises: if the feature browsing attribute value X extracted from a certain user terminal with a newly added user portrait label and the average effect time length Y corresponding to a certain short video advertisement satisfy X≥Y, feeding back to add the certain short video advertisement into the short video sequence to be put for the certain user.

7. An intelligent advertisement delivery management apparatus for performing the intelligent advertisement delivery management method according to any one of claims 1 to 5, characterized by: The device comprises a platform browsing data collection management module, a short video extraction classification module, a browsing degree value evaluation management module, a feature browsing attribute value calculation module, an effect time length extraction management module, and an advertisement intelligent putting management module. The platform browsing data collection management module is used for monitoring the short video platform to collect the browsing data of each user terminal, and monitoring the change of the user portrait label generated for each user terminal; The short video extraction classification module is used for whenever capturing the occurrence of a newly added user portrait label for any user terminal, combing the short video sequence browsed by the user terminal in the process of the newly added user portrait label, and classifying each short video contained in the short video sequence according to the different corresponding user portrait labels; The browsing degree value evaluation management module is used for extracting a plurality of target video sequences according to the distribution of short videos of different categories in the short video sequence, and evaluating the browsing degree value of any target video sequence by the user terminal; The feature browsing attribute value calculation module is used for extracting a plurality of target video sequences according to the distribution of short videos of different categories in the short video sequence, and evaluating the browsing degree value of any target video sequence by the user terminal; The effect time length extraction management module is used for analyzing the change trend of the browsing degree value of different target video sequences presented by the user terminal in the short video sequence, and extracting the feature browsing attribute value of the user terminal; The advertisement intelligent putting management module is used for intelligently putting the user terminal captured to have a newly added user portrait label by matching the feature browsing attribute value of the user terminal with the effect time length of the short video advertisement.

8. A storage medium characterized by: The storage medium has computer instructions stored thereon, and the computer instructions are executed by the processor to implement the intelligent advertisement putting management method in any one of claims 1-6.

9. An intelligent advertisement delivery management device, characterized by comprising: The device comprises a memory and at least one processor, the memory stores computer instructions, and the at least one processor invokes the computer instructions in the memory to enable the intelligent advertisement delivery management device to perform the intelligent advertisement delivery management method according to any one of claims 1-6.

Images