Content operation intelligent monitoring system based on data analysis

Abstract

The invention belongs to the field of content operation, relates to a data analysis technology, is used for solving the problem that in the prior art, a content operation account cannot be subjected to full-life process analysis in combination with big data, and particularly relates to a content operation intelligent monitoring system based on data analysis, which comprises an intelligent monitoring platform, the intelligent monitoring platform is in communication connection with a big data analysis module, a development evaluation module, a delivery management module and a database; the big data analysis module is used for performing big data analysis on the content operation account: marking the analyzed content operation account as an analysis object, and obtaining basic parameters of the analysis object; marking all content operation accounts which conform to account types and content styles and are registered by the intelligent monitoring platform as evaluation objects; according to the method, the release critical value can be obtained after the release set is subjected to numerical cleaning processing, then the advertisement release opportunity of the content operation account is optimized according to the release critical value, and fan maintenance and commercial conversion of the content operation account are considered.

Description

Technical Field

[0001] The present invention belongs to the field of content operation and relates to data analysis technology, and specifically to an intelligent monitoring system for content operation based on data analysis. Background Art

[0002] Content operation refers to a series of activities that increase the content value of Internet products and create user stickiness and activity by creating, editing, organizing, and presenting website or product content. Its core purpose is to attract and retain target users, increase product activity and user stickiness, and ultimately achieve business goals.

[0003] The invention patent with announcement number CN116614679A discloses an optimization processing method and system for short video advertising delivery. The optimization processing method can classify the advertisements to be delivered, obtain the delivery volume ratio of the advertisements to be delivered, and output the delivery adjustment results to solve the problem that the existing technology is insufficient in the collection and analysis of user preferences and related preferences; however, the optimization processing method can only analyze user preferences based on the advertisement type, and cannot combine big data to analyze the entire life cycle of the content operation account, and thus cannot optimize the advertisement delivery start time point, video content release time interval and advertisement insertion position of the content operation account, resulting in the inability to effectively balance user maintenance and advertisement delivery for content operations.

[0004] In view of the above technical problems, this application proposes a solution. Summary of the invention

[0005] The purpose of the present invention is to provide a content operation intelligent monitoring system based on data analysis, which is used to solve the problem that the existing technology cannot combine big data to analyze the entire life cycle of content operation accounts;

[0006] The technical problem to be solved by the present invention is: how to provide a content operation intelligent monitoring system based on data analysis that can combine big data to perform full life cycle analysis on content operation accounts.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] The content operation intelligent monitoring system based on data analysis includes an intelligent monitoring platform, wherein the intelligent monitoring platform is communicatively connected with a big data analysis module, a development evaluation module, a delivery management module and a database;

[0009] The big data analysis module is used to perform big data analysis on content operation accounts: mark the content operation account to be analyzed as the analysis object, and obtain the basic parameters of the analysis object; mark all content operation accounts registered on the intelligent monitoring platform that meet the account type and content style as evaluation objects, and obtain the operation coefficient YY of the evaluation object; mark the L2 evaluation objects with the largest operation coefficient YY values ​​as reference objects, mark the release time point of the video content in which the reference object is first implanted with an advertisement as the monitoring time point, obtain the operation coefficient YY of the reference object at the monitoring time point and mark it as the release coefficient of the reference object, form a release set from the release coefficients of all reference objects, and perform numerical cleaning on the release set to obtain the delivery critical value;

[0010] The development evaluation module is used to perform development evaluation analysis on the content operation account: mark the time between the current system time and the registration time of the analysis object as the operation time, establish a rectangular coordinate system with the operation time as the X-axis and the operation coefficient YY as the Y-axis, and draw the release curve of the analysis object in the rectangular coordinate system; draw the release curves of all reference objects in the same way, intercept the curve with the X-axis projection length of the operation time from the starting point of the release curve of the reference object and mark it as the comparison curve of the reference object; compare and analyze the release curve with the comparison curve and judge whether the development trajectory of the analysis object meets the requirements according to the comparison analysis results;

[0011] The delivery management module is used to perform advertising delivery optimization management and analysis on content operation accounts.

[0012] Furthermore, the basic parameters include account type, content style, current number of fans, like data and comment data. The like data is the average number of likes for the L1 video contents released recently, and the comment data is the average number of comments for the L1 video contents released recently.

[0013] Furthermore, the process of obtaining the operating coefficient YY of the evaluation object includes: obtaining the basic parameters of the evaluation object and obtaining the current operating coefficient YY of the evaluation object through the formula YY=a1×FS+c2×DZ+a3×PL, where FS, DZ and PL are the values ​​of the current number of fans, likes data and comments data of the evaluation object respectively.

[0014] Furthermore, the specific process of performing numerical cleaning on the release set includes: performing variance calculation on all elements in the release set to obtain a reference performance value, obtaining a reference performance threshold through a database, and comparing the reference performance value with the reference performance threshold: if the reference performance value is less than the reference performance threshold, the minimum element in the release set is marked as the delivery critical value; if the reference performance value is greater than or equal to the reference performance threshold, the maximum element and the minimum element in the release set are eliminated, and then the reference performance value of the release set is calculated again, and so on, until the reference performance value is less than the reference performance threshold; the delivery critical value is sent to the mobile terminal of the manager of the analysis object through the intelligent monitoring platform.

[0015] Furthermore, the process of drawing the release curve of the analysis object includes: marking the duration between the time when the analysis object releases the video content and the registration time of the analysis object as the time monitoring value of the video content, marking the operation coefficient YY when the analysis object releases the video content as the operation monitoring value of the video content, marking a number of release points in a rectangular coordinate system with the time monitoring value as the horizontal coordinate and the operation monitoring value as the vertical coordinate, the number of release points is the same as the number of video contents released by the analysis object, and connecting the release points from left to right in sequence and smoothing them to obtain the release curve of the analysis object.

[0016] Furthermore, the specific process of comparing and analyzing the comparison curve with the release curve includes: marking the sum of the area values ​​of all closed figures formed by the comparison curve and the release curve of the analysis object as the trajectory overlap value of the analysis object relative to the reference object, marking the reference object with the smallest trajectory overlap value as the development prediction object, obtaining the trajectory overlap threshold through the database, and comparing the trajectory overlap value with the trajectory overlap threshold: if the trajectory overlap value is less than the trajectory overlap threshold, it is determined that the development trajectory of the analysis object meets the requirements; if the trajectory overlap value is greater than or equal to the trajectory overlap threshold, it is determined that the development trajectory of the analysis object does not meet the requirements, and performing trajectory optimization analysis on the analysis object: obtaining the release parameters of the development prediction object and sending the release parameters to the mobile phone terminal of the manager of the analysis object through the intelligent monitoring platform; the release parameters include the average value of the video content release time interval of the development prediction object, the advertising delivery frequency, and the maximum value of the video content release time interval.

[0017] Furthermore, the specific process of the delivery management module for performing advertising delivery optimization management analysis on the content operation account includes: summing up and averaging the duration of the video content published by the analysis object to obtain the content duration value NS, and obtaining the content duration low value NSd and the content duration high value NSg through the formulas NSd=t1×NS and NSg=t2×NS, wherein t1 and t2 are both proportional coefficients, and 0.85≤t1≤0.95, 1.05≤t2≤1.15; the content duration range is formed by the content duration low value NSd and the content duration high value NSg, and all the video content published by the reference object are marked For management objects, the management objects whose duration is within the content duration range are marked as optimization objects, and the acceleration data JS, jump data TC and conversion data ZH of the optimization objects are obtained, and numerical calculations are performed to obtain the optimization coefficient YH of the optimization objects; the L3 optimization objects with the largest optimization coefficient YH values ​​are marked as standard objects, and the duration of the advertisement playback time and the video start time of the standard objects is marked as the delivery starting value of the standard objects. The maximum and minimum values ​​of the delivery starting values ​​of all standard objects constitute the delivery optimization range, and the delivery optimization range is sent to the mobile terminal of the management personnel of the analysis object through the intelligent monitoring platform.

[0018] Furthermore, the acceleration data JS is the ratio of the number of times the optimized object is accelerated when it is played during the advertising period to the number of views of the optimized object, the jump-out data TC is the ratio of the number of times the user jumps out of the playback interface when the optimized object is played during the advertising period to the number of views of the optimized object, and the conversion data ZH is the ratio of the number of times the advertising link of the optimized object is clicked to the number of views of the optimized object.

[0019] The present invention has the following beneficial effects:

[0020] 1. The big data analysis module can be used to analyze the content operation accounts, screen the reference objects according to the account type, content style and operation coefficient, build a release set according to the release time of the video content where the reference object first inserts advertisements, and obtain the critical value of the release after numerical cleaning of the release set. Then, the advertising release timing of the content operation account can be optimized according to the critical value of the release, taking into account both the fan maintenance and commercial conversion of the content operation account;

[0021] 2. The development evaluation module can be used to conduct development evaluation and analysis on content operation accounts, and obtain the trajectory overlap value of the analysis object relative to the reference object by curve comparison. The development prediction object is then marked according to the trajectory overlap value, and the health of the development trajectory of the analysis object is evaluated in combination with the trajectory overlap value of the analysis object relative to the development prediction object. When the development trajectory does not meet the requirements, the operation is optimized through the release parameters of the development prediction object;

[0022] 3. The delivery management module can be used to perform advertising delivery optimization management and analysis on content operation accounts, mark optimization objects according to the content duration range, and then mark standard objects and delivery optimization ranges according to the optimization coefficients of the optimization objects. According to the delivery optimization range, the timing of advertising insertion when the content operation account publishes videos can be optimized to improve the conversion rate of advertisements. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0025] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] like Figure 1 As shown, the content operation intelligent monitoring system based on data analysis includes an intelligent monitoring platform, which is communicatively connected to a big data analysis module, a development evaluation module, a delivery management module and a database.

[0027] The big data analysis module is used to perform big data analysis on content operation accounts: mark the content operation accounts to be analyzed as analysis objects, and obtain basic parameters of the analysis objects, which include account type, content style, current number of fans, likes data and comment data, where the likes data is the average number of likes for the L1 most recently released video contents, and the comment number is the average number of comments for the L1 most recently released video contents; mark all content operation accounts registered on the intelligent monitoring platform that meet the account type and content style as evaluation objects, obtain basic parameters of the evaluation objects, and obtain the current operation coefficient YY of the evaluation object through the formula YY=a1×FS+c2×DZ+a3×PL, where FS, DZ and PL are the values ​​of the current number of fans, likes data and comment data of the evaluation object, respectively.

[0028] The L2 evaluation objects with the largest operation coefficient YY values ​​are marked as reference objects. The release time point of the video content where the reference object performs the first advertisement implantation is marked as the monitoring time point. The operation coefficient YY of the reference object at the monitoring time point is obtained and marked as the release coefficient of the reference object. The release coefficients of all reference objects constitute a release set.

[0029] The release set is numerically cleaned: the variance of all elements in the release set is calculated to obtain a reference performance value, the reference performance threshold is obtained through the database, and the reference performance value is compared with the reference performance threshold: if the reference performance value is less than the reference performance threshold, the minimum element in the release set is marked as the delivery critical value; if the reference performance value is greater than or equal to the reference performance threshold, the maximum element and the minimum element in the release set are eliminated, and then the reference performance value of the release set is calculated again, and so on, until the reference performance value is less than the reference performance threshold; the delivery critical value is sent to the mobile phone terminal of the manager of the analysis object through the intelligent monitoring platform; the reference object is screened according to the account type, content style and operation coefficient, and the release set is constructed according to the release time point of the video content where the reference object first inserts an advertisement, and the delivery critical value is obtained after the release set is numerically cleaned, and then the advertising delivery timing of the content operation account is optimized according to the delivery critical value, taking into account the fan maintenance and commercial conversion of the content operation account.

[0030] The development evaluation module is used to perform development evaluation analysis on content operation accounts: the duration between the current system time and the registration time of the analysis object is marked as the operation duration, a rectangular coordinate system is established with the operation duration as the X-axis and the operation coefficient YY as the Y-axis, the duration between the time when the analysis object releases the video content and the registration time of the analysis object is marked as the time monitoring value of the video content, the operation coefficient YY when the analysis object releases the video content is marked as the operation monitoring value of the video content, a number of publishing points are marked in the rectangular coordinate system with the time monitoring value as the horizontal coordinate and the operation monitoring value as the vertical coordinate, the number of publishing points is the same as the number of video content already published by the analysis object, the publishing points are connected from left to right in sequence and smoothed to obtain the publishing curve of the analysis object.

[0031] Draw the release curves of all reference objects in the same way, intercept the curve with the X-axis projection length of the operation time from the starting point of the release curve of the reference object and mark it as the comparison curve of the reference object; compare and analyze the release curve of the analysis object with the comparison curve: mark the sum of the area values ​​of all closed figures formed by the comparison curve and the release curve of the analysis object as the trajectory overlap value of the analysis object relative to the reference object, mark the reference object with the smallest trajectory overlap value as the development prediction object, obtain the trajectory overlap threshold through the database, and compare the trajectory overlap value with the trajectory overlap threshold: if the trajectory overlap value is less than the trajectory overlap threshold, it is determined that the development trajectory of the analysis object meets the requirements; if the trajectory overlap value is greater than or equal to the trajectory overlap threshold, it is determined that the development trajectory of the analysis object does not meet the requirements.

[0032] When the development trajectory of the analysis object does not meet the requirements, a trajectory optimization analysis is performed on the analysis object: the release parameters of the development prediction object are obtained and sent to the mobile terminal of the manager of the analysis object through the intelligent monitoring platform; the release parameters include the average value of the video content release time interval of the development prediction object, the advertising delivery frequency, and the maximum value of the video content release time interval; the trajectory overlap value of the analysis object relative to the reference object is obtained by curve comparison, and the development prediction object is marked according to the trajectory overlap value, and the health of the development trajectory of the analysis object is evaluated in combination with the trajectory overlap value of the analysis object relative to the development prediction object. When the development trajectory does not meet the requirements, operational optimization is performed through the release parameters of the development prediction object.

[0033] The delivery management module is used to perform advertising delivery optimization management analysis on the content operation account: the duration of the video content published by the analysis object is summed and averaged to obtain the content duration value NS, and the low value NSd of the content duration and the high value NSg of the content duration are obtained by the formula NSd=t1×NS and NSg=t2×NS, wherein t1 and t2 are both proportional coefficients, and 0.85≤t1≤0.95, 1.05≤t2≤1.15; the low value NSd of the content duration and the high value NSg of the content duration constitute the content duration range, and all reference objects have been The published video content is marked as a management object, and the management object whose duration is within the content duration range is marked as an optimization object. The acceleration data JS, jump-out data TC and conversion data ZH of the optimization object are obtained. The acceleration data JS is the ratio of the number of times the optimization object is accelerated when it is played during the advertising period to the number of views of the optimization object. The jump-out data TC is the ratio of the number of times the user jumps out of the playback interface when the optimization object is played during the advertising period to the number of views of the optimization object. The conversion data ZH is the ratio of the number of clicks on the advertising link of the optimization object to the number of views of the optimization object.

[0034] The optimization coefficient YH of the optimization object is obtained by the formula YH=k1×JS+k2×TC-k3×ZH, where k1, k2 and k3 are all proportional coefficients, and k1>k2>k3>1; the L3 optimization objects with the largest optimization coefficient YH values ​​are marked as standard objects, and the duration of the advertisement playback time and the video start time of the standard objects is marked as the delivery starting value of the standard objects. The maximum and minimum values ​​of the delivery starting values ​​of all standard objects constitute the delivery optimization range, and the delivery optimization range is sent to the mobile terminal of the manager of the analysis object through the intelligent monitoring platform; the optimization objects are marked according to the content duration range, and then the standard objects and the delivery optimization range are marked by the optimization coefficients of the optimization objects. According to the delivery optimization range, the timing of advertisement insertion when the content operation account publishes the video is optimized to improve the conversion rate of the advertisement.

[0035] The content operation intelligent monitoring system based on data analysis performs big data analysis on the content operation account and obtains the critical value of the analysis object when working, and performs development evaluation analysis on the content operation account: the time between the current system time and the registration time of the analysis object is marked as the operation time, and a rectangular coordinate system is established with the operation time as the X-axis and the operation coefficient YY as the Y-axis. The release curve of the analysis object and the comparison curve of the reference object are drawn in the rectangular coordinate system, and the release curve of the analysis object is compared with the comparison curve to obtain the trajectory overlap value, and the reference object with the smallest trajectory overlap value is marked as the development prediction object; the content operation account is subjected to advertising delivery optimization management analysis and the delivery optimization range is marked.

[0036] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

[0037] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula close to the real value. The coefficients in the formula are set by technicians in this field according to the actual situation; for example: formula YY = a1×FS+c2×DZ+a3×PL; technicians in this field collect multiple groups of sample data and set corresponding operating coefficients for each group of sample data; substitute the set operating coefficients and the collected sample data into the formula, any three formulas constitute a three-variable linear equation group, screen the calculated coefficients and take the average, and obtain the values ​​of a1, a2 and a3 as 4.83, 2.69 and 2.42 respectively;

[0038] The size of the coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the coefficient depends on the amount of sample data and the initial setting of the corresponding operating coefficient for each set of sample data by technical personnel in this field; as long as it does not affect the proportional relationship between the parameter and the quantified value, such as the operating coefficient is proportional to the current number of fans.

[0039] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0040] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. The intelligent monitoring system for content operation based on data analysis is characterized by: It includes an intelligent monitoring platform, which is communicatively connected to a big data analysis module, a development evaluation module, a delivery management module and a database; The big data analysis module is used to perform big data analysis on content operation accounts: mark the content operation account to be analyzed as an analysis object, and obtain the basic parameters of the analysis object; mark all content operation accounts registered on the intelligent monitoring platform that meet the account type and content style as evaluation objects, and obtain the operation coefficient YY of the evaluation object; Mark the L2 evaluation objects with the largest operation coefficient YY as reference objects, mark the release time point of the video content where the reference object first inserts advertisements as the monitoring time point, obtain the operation coefficient YY of the reference object at the monitoring time point and mark it as the release coefficient of the reference object, form a release set with the release coefficients of all reference objects, and perform numerical cleaning on the release set to obtain the critical value of placement; The development evaluation module is used to perform development evaluation analysis on the content operation account: mark the time between the current system time and the registration time of the analysis object as the operation time, establish a rectangular coordinate system with the operation time as the X-axis and the operation coefficient YY as the Y-axis, and draw the release curve of the analysis object in the rectangular coordinate system; draw the release curves of all reference objects in the same way, intercept the curve with the X-axis projection length of the operation time from the starting point of the release curve of the reference object and mark it as the comparison curve of the reference object; compare and analyze the release curve with the comparison curve and judge whether the development trajectory of the analysis object meets the requirements according to the comparison analysis results; The delivery management module is used to perform advertising delivery optimization management and analysis on content operation accounts.

2. The content operation intelligent monitoring system based on data analysis according to claim 1 is characterized in that: The basic parameters include account type, content style, current number of followers, like data, and comment data. The like data is the average number of likes for the L1 most recently released video contents, and the comment data is the average number of comments for the L1 most recently released video contents.

3. The content operation intelligent monitoring system based on data analysis according to claim 2 is characterized in that: The process of obtaining the operating coefficient YY of the evaluation object includes: obtaining the basic parameters of the evaluation object and obtaining the current operating coefficient YY of the evaluation object through the formula YY=a1×FS+c2×DZ+a3×PL, where FS, DZ and PL are the values ​​of the current number of fans, likes data and comments data of the evaluation object respectively.

4. The content operation intelligent monitoring system based on data analysis according to claim 3 is characterized in that: The specific process of numerical cleaning of the release set includes: performing variance calculation on all elements in the release set to obtain a reference performance value, obtaining a reference performance threshold through a database, and comparing the reference performance value with the reference performance threshold: if the reference performance value is less than the reference performance threshold, the minimum element in the release set is marked as the critical value for delivery; if the reference performance value is greater than or equal to the reference performance threshold, the maximum element and the minimum element in the release set are eliminated, and then the reference performance value of the release set is calculated again, and so on, until the reference performance value is less than the reference performance threshold; the critical value for delivery is sent to the mobile terminal of the manager of the analysis object through the intelligent monitoring platform.

5. The content operation intelligent monitoring system based on data analysis according to claim 4 is characterized in that: The process of drawing the release curve of the analysis object includes: marking the duration between the time when the analysis object releases the video content and the registration time of the analysis object as the time monitoring value of the video content, marking the operation coefficient YY when the analysis object releases the video content as the operation monitoring value of the video content, marking a number of release points in a rectangular coordinate system with the time monitoring value as the horizontal coordinate and the operation monitoring value as the vertical coordinate. The number of release points is the same as the number of video contents that the analysis object has released. The release points are connected from left to right in sequence and smoothed to obtain the release curve of the analysis object.

6. The content operation intelligent monitoring system based on data analysis according to claim 5 is characterized in that: The specific process of comparing and analyzing the comparison curve with the release curve includes: marking the sum of the area values ​​of all closed figures formed by the comparison curve and the release curve of the analysis object as the trajectory overlap value of the analysis object relative to the reference object, marking the reference object with the smallest trajectory overlap value as the development prediction object, obtaining the trajectory overlap threshold through the database, and comparing the trajectory overlap value with the trajectory overlap threshold: if the trajectory overlap value is less than the trajectory overlap threshold, it is determined that the development trajectory of the analysis object meets the requirements; if the trajectory overlap value is greater than or equal to the trajectory overlap threshold, it is determined that the development trajectory of the analysis object does not meet the requirements, and a trajectory optimization analysis is performed on the analysis object: obtaining the release parameters of the development prediction object and sending the release parameters to the mobile phone terminal of the manager of the analysis object through the intelligent monitoring platform; the release parameters include the average value of the video content release time interval of the development prediction object, the advertising delivery frequency, and the maximum value of the video content release time interval.

7. The content operation intelligent monitoring system based on data analysis according to claim 6 is characterized in that: The specific process of the delivery management module for optimizing the management and analysis of the advertising delivery of the content operation account includes: summing up and averaging the duration of the video content published by the analysis object to obtain the content duration value NS, and obtaining the content duration low value NSd and the content duration high value NSg by the formula NSd=t1×NS and NSg=t2×NS, wherein t1 and t2 are both proportional coefficients, and 0.85≤t1≤0.95, 1.05≤t2≤1.15; the content duration range is formed by the content duration low value NSd and the content duration high value NSg, and all the video contents published by the reference object are marked as management Management objects, mark the management objects whose duration is within the content duration range as optimization objects, obtain the acceleration data JS, jump data TC and conversion data ZH of the optimization objects, and perform numerical calculation to obtain the optimization coefficient YH of the optimization objects; mark the L3 optimization objects with the largest optimization coefficient YH as standard objects, mark the duration of the advertisement playback time and the video start time of the standard objects as the delivery starting value of the standard objects, and the maximum and minimum values ​​of the delivery starting values ​​of all standard objects constitute the delivery optimization range, and send the delivery optimization range to the mobile terminal of the management personnel of the analysis object through the intelligent monitoring platform.

8. The content operation intelligent monitoring system based on data analysis according to claim 7 is characterized in that: The acceleration data JS is the ratio of the number of times the optimized object is accelerated when it is played during the advertising period to the number of views of the optimized object. The jump-out data TC is the ratio of the number of times the user jumps out of the playback interface when the optimized object is played during the advertising period to the number of views of the optimized object. The conversion data ZH is the ratio of the number of clicks on the advertising link of the optimized object to the number of views of the optimized object.

Images