Advertisement putting effect intelligent monitoring method and system based on cloud video data analysis

Abstract

The invention discloses an intelligent advertisement putting effect monitoring method and system based on cloud video data analysis, and relates to the field of intelligent monitoring. Advertisement feature information is generated through cloud video platform server data, and user behavior information is generated according to thread data fluctuation conditions; acquiring a behavior difference value according to the behavior information difference before and after the user browses the advertisement, and generating advertisement acceptance in combination with the advertisement feature information; obtaining advertisement putting historical data, and generating an advertisement induction search probability; combining the advertisement acceptability, the behavior difference value and the advertisement induction search probability to generate an advertisement effect evaluation value and an advertisement audience portrait; analyzing the advertisement induction search probability and the advertisement audience portrait according to the advertisement putting historical data, and setting a user putting effect threshold value; and analyzing the advertisement effect evaluation value based on the user putting effect threshold value, and judging whether the advertisement effect evaluation value is greater than the user putting effect threshold value or not.

Description

Technical Field

[0001] The present invention relates to the field of intelligent monitoring, and in particular to a method and system for intelligently monitoring advertising effects based on cloud video data analysis. Background Art

[0002] Cloud video data analysis refers to the process of collecting, storing, processing and analyzing video content, user behavior, playback effects and other data through cloud computing platforms, using the powerful computing power and massive data storage capacity of cloud computing to improve the quality of video content and user experience. Advertising effect refers to the comprehensive impact of advertising in multiple aspects such as communication, brand building and sales promotion after advertising is released. It is a key indicator to measure whether an advertisement is successful.

[0003] Existing intelligent monitoring methods and systems for advertising delivery effects usually collect data from a single platform, which makes the acquired data incomplete. Only simple statistical analysis can be performed on the acquired data, and it is impossible to understand the characteristics of users in detail. For the delivery effect, it can only monitor whether the advertisement is viewed by the user. It is difficult to conduct in-depth data analysis of the user's behavioral motivations, and the intentions of users' complex behaviors are ignored, resulting in a large difference between the monitoring results and the actual advertising delivery effects, making it impossible to meet the delivery effects required by the advertisers. Summary of the invention

[0004] In order to solve the above technical problems, a method and system for intelligent monitoring of advertising delivery effects based on cloud video data analysis are provided. This technical solution solves the problems raised in the above background technology, that is, it is impossible to understand the characteristics of users in detail, it is difficult to conduct in-depth data analysis of users' behavioral motivations, and the intentions of users' complex behaviors are ignored, resulting in a large difference between the monitoring results and the actual advertising delivery effects.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] An intelligent monitoring method for advertising delivery effect based on cloud video data analysis, comprising:

[0007] Obtain and analyze cloud video platform server data to generate advertising feature information and user behavior information;

[0008] Based on user behavior information, obtain behavior difference values, combine with advertising feature information, and generate advertising acceptance;

[0009] Based on the cloud video platform, historical data of advertising delivery is obtained to generate the probability of advertising-induced searches;

[0010] Generate advertising effect evaluation value and advertising audience information based on advertising acceptance, behavioral difference value and advertising-induced search probability;

[0011] Classify advertising audience information and generate advertising audience portraits;

[0012] Based on historical advertising data, analyze the probability of advertising-induced searches and advertising audience portraits, and set user delivery effect thresholds;

[0013] Based on the user delivery effect threshold, the advertising effect evaluation value is analyzed to determine whether the advertising effect evaluation value is greater than the user delivery effect threshold. If so, the advertising content is optimized according to the advertising audience portrait to maintain the audience's freshness and attention to the advertisement. If not, the advertising delivery is adjusted according to the advertising audience portrait.

[0014] Preferably, the generating of advertisement feature information and user behavior information specifically includes:

[0015] Processing the cloud video platform server data to obtain server thread occupancy and advertising information, wherein the advertising information includes advertising product content and advertising duration;

[0016] Generate advertisement feature information according to the advertisement product content;

[0017] Obtain the user's login ID on the cloud video platform, bind the user's login ID to the server thread based on the cloud video server data, and obtain the user-associated thread;

[0018] Analyze the server thread occupancy according to the user-associated thread to obtain thread fluctuation performance information, wherein the thread fluctuation performance information includes execution state fluctuation performance information, thread quantity fluctuation performance information and resource occupancy fluctuation performance information;

[0019] Generate user behavior information based on thread fluctuation performance information;

[0020] Through the execution status fluctuation performance information of the user-associated thread, it is determined whether the user has paused the video playback; through the thread number fluctuation performance information of the user-associated thread, it is determined whether the user has interacted with the video; through the resource usage fluctuation performance information of the user-associated thread, it is determined whether the user has downloaded the video.

[0021] Preferably, the step of obtaining the behavior difference value and combining it with the advertisement feature information to generate the advertisement acceptance specifically includes:

[0022] Obtain thread fluctuation time based on cloud video platform server data and thread fluctuation performance information;

[0023] Analyze resource usage fluctuations based on ad duration and determine ad time slots;

[0024] Divide the thread fluctuation time according to the advertising period, and generate the thread occupancy information of the pre-ad period and the post-ad period in combination with the server thread occupancy status;

[0025] Taking three minutes as a time period, analyzing the execution state fluctuation performance information, the thread number fluctuation performance information and the resource occupancy fluctuation performance information, and obtaining the execution state fluctuation frequency information, the thread number fluctuation frequency information and the resource occupancy fluctuation frequency information;

[0026] Analyze the thread occupancy information of the pre-ad period and the post-ad period from the perspectives of execution status, thread number, and resource occupancy fluctuations, and generate execution status fluctuation frequency difference, thread number fluctuation frequency difference, and resource occupancy fluctuation frequency difference respectively;

[0027] Based on the Pearson correlation coefficient calculation formula, the execution state fluctuation frequency difference is used as the benchmark variable, and the thread number fluctuation frequency difference and resource occupancy fluctuation frequency difference are analyzed to obtain the thread number fluctuation correlation coefficient and resource occupancy fluctuation correlation coefficient respectively;

[0028] The behavior difference value is obtained by obtaining the ratio of the correlation coefficient of thread quantity fluctuation and the correlation coefficient of resource occupancy fluctuation;

[0029] Generate an advertising perception table based on historical advertising data;

[0030] Substitute the advertising feature information into the advertising perception table to obtain the standard difference value, combine it with the behavioral difference value, generate advertising acceptance, and calculate the advertising acceptance state transition probability of different behavioral difference values ​​to establish an advertising acceptance matrix.

[0031] Preferably, generating the advertisement-induced search probability specifically includes:

[0032] Organize historical data on advertising, divide it by advertising acceptance, and generate user impact status information;

[0033] According to the user influence status information, the historical data of advertising delivery is analyzed, the user status probabilities with different acceptance levels are calculated, and the user influence status transition probability matrix is ​​generated;

[0034] Analyze the advertisement acceptance matrix and the user influence state transition probability matrix to generate advertisement-induced search probability;

[0035] The specific calculation formula for the probability of advertisement-induced search is:

[0036] P[s k+1 |s k ]=P[s1|s2,s3,s4]P[v|v1,v2,v3];

[0037] In the formula, P[s k+1 |s k ] is the probability of advertisement-induced search, s k+1 is the impact state of the k+1th user, s k is the kth user influence state, s1, s2, s3, s4 are user influence states, v is the current advertising acceptance state, v1, v2, v3 are advertising acceptance states, P[s1|s2,s3,s4] is the user influence state transition probability, and P[v|v1,v2,v3] is the advertising acceptance state transition probability.

[0038] Preferably, the generating of the advertising effect evaluation value and the advertising audience information specifically includes:

[0039] Obtain the registration information of the user login ID, classify the user information based on the advertising acceptance, obtain the average advertising acceptance of different user groups, and generate advertising audience information;

[0040] Obtain the total number of ad viewers, and combine it with ad audience information to determine the distribution of different user groups in the total number of ad viewers;

[0041] The advertising effect evaluation value is generated by taking a weighted sum of the advertising-induced search probability corresponding to the average advertising acceptance of each user group and the distribution of each user group in the total number of advertisement viewers.

[0042] Preferably, the setting of the user delivery effect threshold specifically includes:

[0043] According to the advertising audience portrait, the historical data of the same type of advertising is classified according to age information and regional information, and the age advertising effect data and regional advertising effect data are generated;

[0044] The age-based delivery effect data and the regional delivery effect data are collated and analyzed respectively to obtain the age-based delivery effect peak data, age-based delivery effect valley data, regional delivery effect peak data, and regional delivery effect valley data;

[0045] The age delivery effect peak data and the age delivery effect valley data are averaged and summed to generate the age delivery effect threshold; the region delivery effect peak data and the region delivery effect valley data are averaged and summed to generate the region delivery effect threshold;

[0046] According to the registration information of the user browsing the advertisement, the corresponding age delivery effect threshold and region delivery effect threshold are obtained, and the average value is calculated to generate the user delivery effect threshold.

[0047] Furthermore, an intelligent monitoring system for advertising delivery effect based on cloud video data analysis is proposed to implement the above-mentioned monitoring method, which is characterized by specifically including:

[0048] A data collection module, which is used to establish a data connection with the cloud video platform server, obtain cloud video platform server data, obtain advertising information from the advertiser, and transmit the collected information data to the feature extraction module and the data analysis module;

[0049] A feature extraction module, which is used to extract features from the received data according to the required requirements, generate advertisement feature information according to the advertisement product content, extract the user's age information and region information according to the registration information of the user login ID, and transmit the extracted feature information to the data analysis module;

[0050] A data analysis module, which is used to analyze and process the received data, and to generate thread fluctuation performance information, behavior difference value, advertisement acceptance, advertisement-induced search probability, advertisement effect evaluation value, advertisement audience information, advertisement audience portrait and user delivery effect threshold by collating and analyzing the data of the data collection module and the feature extraction module, and transmit the data to the intelligent monitoring module and the effect display module;

[0051] An intelligent monitoring module, which is used to compare the advertising effect evaluation value transmitted by the data analysis module with the user delivery effect threshold, monitor whether the advertising effect evaluation value meets the standard, and transmit the monitoring result to the effect display module;

[0052] The effect display module is used to analyze and organize the received data and display the advertising monitoring results.

[0053] Preferably, the data collection module specifically includes:

[0054] A first collecting unit, wherein the first collecting unit is used to establish a data connection with a cloud video platform server and obtain thread information from the cloud video platform server;

[0055] The second collecting unit is used to establish a communication connection with the advertiser and obtain the advertisement information from the advertiser.

[0056] Preferably, the feature extraction module specifically includes:

[0057] A first extraction unit, the first extraction unit is used to extract features from the received advertisement information, generate advertisement product content and advertisement duration, and generate advertisement feature information according to the advertisement product content;

[0058] The second extraction unit is used to extract data features of the received user ID registration information according to age and region to generate an advertising audience portrait.

[0059] Preferably, the data analysis module specifically includes:

[0060] A first analysis unit, the first analysis unit is used to analyze the received thread fluctuation performance information to generate execution state fluctuation performance information, thread number fluctuation performance information and resource occupancy fluctuation performance information;

[0061] A second analysis unit, the second analysis unit is used to analyze the resource occupancy fluctuation time according to the advertisement duration to determine the advertisement time period;

[0062] A third analysis unit, the third analysis unit is used to analyze the thread quantity fluctuation frequency difference and the resource occupancy fluctuation frequency difference by taking the execution state fluctuation frequency difference as a reference variable, and obtain the thread quantity fluctuation correlation coefficient and the resource occupancy fluctuation correlation coefficient respectively;

[0063] The fourth analysis unit, the third analysis unit is used to analyze the advertisement acceptance matrix and the user influence state transition probability matrix through the specific calculation formula of the advertisement induced search probability, and generate the advertisement induced search probability.

[0064] Compared with the prior art, the present invention has the following beneficial effects:

[0065] The present invention proposes an intelligent monitoring scheme for advertising delivery effect based on cloud video data analysis. Through cloud video platform server data, advertising feature information and user behavior information are generated. Based on the user behavior information, a behavior difference value is obtained. In combination with the advertising feature information, advertising acceptance is generated. Through advertising delivery history data, an advertising induced search probability is generated. In combination with the advertising acceptance, the behavior difference value and the advertising induced search probability, an advertising effect evaluation value and an advertising audience portrait are generated. According to the advertising delivery history data, the advertising induced search probability and the advertising audience portrait are analyzed. A user delivery effect threshold is set. Based on the user delivery effect threshold, the advertising effect evaluation value is analyzed to determine whether the advertising effect evaluation value is greater than the user delivery effect threshold. In this way, the user's behavior information can be effectively obtained according to the thread data fluctuation in the cloud video platform server. The advertising acceptance is generated by the difference in the user's behavior information before and after browsing the advertisement. In combination with the advertising delivery history data, the user's behavior motivation is analyzed, so that the evaluation result of the advertising effect is more accurate, the difference between the monitoring result and the actual advertising delivery effect is reduced, and it is guaranteed that the advertiser can understand the advertising delivery effect more clearly. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1This is a flow chart of the method for intelligently monitoring the advertising effect based on cloud video data analysis proposed by the present invention;

[0067] Figure 2 A flowchart of the steps of generating advertisement feature information and user behavior information in the present invention;

[0068] Figure 3 A flowchart of the steps of obtaining behavior difference values ​​and generating advertisement acceptance in the present invention;

[0069] Figure 4 A flow chart of the steps for generating advertisement-induced search probability in the present invention;

[0070] Figure 5 A flowchart of the steps of generating an advertisement effect evaluation value and advertisement audience information in the present invention;

[0071] Figure 6 A flowchart of the steps for setting a user delivery effect threshold in the present invention;

[0072] Figure 7 This is a structural diagram of the intelligent monitoring system for advertising delivery effects based on cloud video data analysis proposed by the present invention. DETAILED DESCRIPTION

[0073] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0074] Reference Figure 1 As shown, a method for intelligently monitoring the effect of advertising based on cloud video data analysis includes:

[0075] Obtain and analyze cloud video platform server data to generate advertising feature information and user behavior information;

[0076] Based on user behavior information, obtain behavior difference values, combine with advertising feature information, and generate advertising acceptance;

[0077] Based on the cloud video platform, historical data of advertising delivery is obtained to generate the probability of advertising-induced searches;

[0078] Generate advertising effect evaluation value and advertising audience information based on advertising acceptance, behavioral difference value and advertising-induced search probability;

[0079] Classify advertising audience information and generate advertising audience portraits;

[0080] Based on historical advertising data, analyze the probability of advertising-induced searches and advertising audience portraits, and set user delivery effect thresholds;

[0081] Based on the user delivery effect threshold, the advertising effect evaluation value is analyzed to determine whether the advertising effect evaluation value is greater than the user delivery effect threshold. If so, the advertising content is optimized according to the advertising audience portrait to maintain the audience's freshness and attention to the advertisement. If not, the advertising delivery is adjusted according to the advertising audience portrait.

[0082] This solution generates advertising feature information and user behavior information through cloud video platform server data, obtains behavior difference values ​​based on user behavior information, generates advertising acceptance in combination with advertising feature information, generates advertising-induced search probability through advertising delivery history data, generates advertising effect evaluation values ​​and advertising audience portraits in combination with advertising acceptance, behavior difference values ​​and advertising-induced search probability, analyzes advertising-induced search probability and advertising audience portraits based on advertising delivery history data, sets user delivery effect thresholds, analyzes advertising effect evaluation values ​​based on user delivery effect thresholds, and determines whether the advertising effect evaluation value is greater than the user delivery effect threshold. In this way, user behavior information can be effectively obtained based on thread data fluctuations in the cloud video platform server, advertising acceptance is generated by comparing the differences in user behavior information before and after browsing advertisements, and user behavior motivations are analyzed in combination with advertising delivery history data, making the evaluation results of advertising effects more accurate.

[0083] Reference Figure 2 As shown, advertisement feature information and user behavior information are generated, including:

[0084] Processing the cloud video platform server data to obtain server thread occupancy and advertising information, wherein the advertising information includes advertising product content and advertising duration;

[0085] Generate advertisement feature information according to the advertisement product content;

[0086] Obtain the user's login ID on the cloud video platform, bind the user's login ID to the server thread based on the cloud video server data, and obtain the user-associated thread;

[0087] Analyze the server thread occupancy according to the user-associated thread to obtain thread fluctuation performance information, wherein the thread fluctuation performance information includes execution state fluctuation performance information, thread quantity fluctuation performance information and resource occupancy fluctuation performance information;

[0088] Generate user behavior information based on thread fluctuation performance information;

[0089] Through the execution status fluctuation performance information of the user-associated thread, it is determined whether the user has paused the video playback; through the thread number fluctuation performance information of the user-associated thread, it is determined whether the user has interacted with the video; through the resource usage fluctuation performance information of the user-associated thread, it is determined whether the user has downloaded the video.

[0090] It can be understood that the cloud video platform server data includes cloud video server data and advertising information implanted by advertisers in the cloud video platform server. According to the content of the advertising product, the content of the advertisement is refined from the perspectives of product type, product spokesperson, product function and product advantage to generate advertising feature information. When the user logs in to the cloud video platform, the user will send a login request to the cloud video platform server. The cloud video platform server will generate an independent data space based on the user's network communication address to record the user's thread data on the cloud video platform. The thread data corresponds to the user's operation behavior. By binding the user's login ID on the cloud video platform with the network communication address, the user-associated thread can be obtained. The thread fluctuation performance information maintains a one-to-one correspondence with the user behavior. The execution status of the thread is divided into start, pause, resume and stop. Start means that the user has opened a new video, pause means that the user has paused the video being watched, resume means that the user continues to play the paused video, and stop means that the user has closed the video. The increase in the number of threads indicates that the user has interacted with the video content while the current video is playing normally. The increase in thread resource usage indicates that the user has downloaded the video.

[0091] Reference Figure 3 As shown, the behavior difference value is obtained, combined with the advertising feature information, to generate the advertising acceptance, which specifically includes:

[0092] Obtain thread fluctuation time based on cloud video platform server data and thread fluctuation performance information;

[0093] Analyze resource usage fluctuations based on ad duration and determine ad time slots;

[0094] Divide the thread fluctuation time according to the advertising period, and generate the thread occupancy information of the pre-ad period and the post-ad period in combination with the server thread occupancy status;

[0095] Taking three minutes as a time period, analyzing the execution state fluctuation performance information, the thread number fluctuation performance information and the resource occupancy fluctuation performance information, and obtaining the execution state fluctuation frequency information, the thread number fluctuation frequency information and the resource occupancy fluctuation frequency information;

[0096] Analyze the thread occupancy information of the pre-ad period and the post-ad period from the perspectives of execution status, thread number, and resource occupancy fluctuations, and generate execution status fluctuation frequency difference, thread number fluctuation frequency difference, and resource occupancy fluctuation frequency difference respectively;

[0097] Based on the Pearson correlation coefficient calculation formula, the execution state fluctuation frequency difference is used as the benchmark variable, and the thread number fluctuation frequency difference and resource occupancy fluctuation frequency difference are analyzed to obtain the thread number fluctuation correlation coefficient and resource occupancy fluctuation correlation coefficient respectively;

[0098] The behavior difference value is obtained by obtaining the ratio of the correlation coefficient of thread quantity fluctuation and the correlation coefficient of resource occupancy fluctuation;

[0099] Generate an advertising perception table based on historical advertising data;

[0100] Substitute the advertising feature information into the advertising perception table to obtain the standard difference value, combine it with the behavioral difference value, generate advertising acceptance, and calculate the advertising acceptance state transition probability of different behavioral difference values ​​to establish an advertising acceptance matrix.

[0101] It is understandable that when thread information fluctuates, the cloud video platform server will record the corresponding time. Therefore, by sorting out the cloud video platform server data through the thread fluctuation performance information, the thread fluctuation time can be obtained. When an advertisement is played in the video, the thread execution state becomes paused, and the number of threads will increase by one thread. The resource occupancy will maintain an increased steady state within the same length of time as the advertisement. Through these characteristic information, the cloud video platform server data can be retrieved to determine the advertising time period. The thread number fluctuation correlation coefficient is the correlation coefficient between the execution state fluctuation frequency difference and the thread number fluctuation frequency difference. The resource occupancy fluctuation correlation coefficient is the correlation coefficient between the execution state fluctuation frequency difference and the resource occupancy fluctuation frequency difference. According to the historical data of advertising delivery, different product types, product spokespersons, and product functions can be obtained. The historical behavior difference values ​​corresponding to the product advantages are compared in turn by the control variable method, and the historical average behavior difference values ​​of the single feature information corresponding to the product type, product spokesperson, product function and product advantage information are obtained respectively. The historical behavior average difference values ​​of the single feature information are statistically integrated to generate an advertising perception table. The advertising acceptance is divided into high acceptance, medium acceptance and low acceptance. There is a corresponding relationship between the behavior difference value and the advertising acceptance, but there are individual differences between users, and there will be a situation where the user's behavior difference value corresponds to the advertising acceptance. By calculating the proportion of users whose behavior difference values ​​in the historical data correspond to the advertising acceptance that have shifted in the total number of users in the historical data, the probability of advertising acceptance state transition for different behavior difference values ​​is determined, and an advertising acceptance matrix is ​​established.

[0102] Reference Figure 4 As shown, the probability of advertisement-induced search is generated, including:

[0103] Organize historical data on advertising, divide it by advertising acceptance, and generate user impact status information;

[0104] According to the user influence status information, the historical data of advertising delivery is analyzed, the user status probabilities with different acceptance levels are calculated, and the user influence status transition probability matrix is ​​generated;

[0105] Analyze the advertisement acceptance matrix and the user influence state transition probability matrix to generate advertisement-induced search probability;

[0106] The specific calculation formula for the probability of advertisement-induced search is:

[0107] P[s k+1 |s k ]=P[s1|s2,s3,s4]P[v|v1,v2,v3];

[0108] In the formula, P[s k+1 |s k ] is the probability of advertisement-induced search, s k+1 is the impact state of the k+1th user, s k is the kth user influence state, s1, s2, s3, s4 are user influence states, v is the current advertising acceptance state, v1, v2, v3 are advertising acceptance states, P[s1|s2,s3,s4] is the user influence state transition probability, and P[v|v1,v2,v3] is the advertising acceptance state transition probability.

[0109] It can be understood that user influence states are divided into users who are not affected by advertisements, users who have a certain interest in advertisements but have not triggered a search, users who click on advertisements and start searching, and users who leave the search page without completing a search. By sorting out historical data on advertisement delivery according to advertisement acceptance, we can obtain user influence states corresponding to different advertisement acceptances. By sorting out and analyzing historical data on advertisement delivery, we can calculate the proportion of the number of people whose user influence states have changed corresponding to the advertisement acceptance in the historical data to the total number of people in the historical data, determine the user state probabilities at different acceptance levels, and establish a user influence state transfer probability matrix.

[0110] Reference Figure 5 As shown, the advertising effect evaluation value and advertising audience information are generated, including:

[0111] Obtain the registration information of the user login ID, classify the user information based on the advertising acceptance, obtain the average advertising acceptance of different user groups, and generate advertising audience information;

[0112] Obtain the total number of ad viewers, and combine it with ad audience information to determine the distribution of different user groups in the total number of ad viewers;

[0113] The advertising effect evaluation value is generated by taking a weighted sum of the advertising-induced search probability corresponding to the average advertising acceptance of each user group and the distribution of each user group in the total number of advertisement viewers.

[0114] It is understandable that the registration information of the user login ID includes the user's age information and the user's geographical location information. Based on the registration information of the user login ID, the users are classified by age and region to generate users of different age groups and users of different regional groups. The different age groups are divided into ten-year intervals, and the users of different regional groups are divided into city-based intervals. Based on the advertising acceptance corresponding to different users in the historical data of advertising delivery, the average advertising acceptance of each user group is calculated, the average advertising acceptance of each user group is compared and arranged in order of average acceptance from high to low to generate advertising audience information.

[0115] Reference Figure 6 As shown, set the user delivery effect threshold, including:

[0116] According to the advertising audience portrait, the historical data of the same type of advertising is classified according to age information and regional information, and the age advertising effect data and regional advertising effect data are generated;

[0117] The age-based delivery effect data and the regional delivery effect data are collated and analyzed respectively to obtain the age-based delivery effect peak data, age-based delivery effect valley data, regional delivery effect peak data, and regional delivery effect valley data;

[0118] The age delivery effect peak data and the age delivery effect valley data are averaged and summed to generate the age delivery effect threshold; the region delivery effect peak data and the region delivery effect valley data are averaged and summed to generate the region delivery effect threshold;

[0119] According to the registration information of the user browsing the advertisement, the corresponding age delivery effect threshold and region delivery effect threshold are obtained, and the average value is calculated to generate the user delivery effect threshold.

[0120] Further, see Figure 7 As shown, an intelligent monitoring system for advertising delivery effect based on cloud video data analysis is proposed, which is used to implement the above-mentioned monitoring method, and is characterized in that it specifically includes:

[0121] The data collection module is used to establish data connection with the cloud video platform server, obtain data from the cloud video platform server, obtain advertising information from the advertiser, and transmit the collected information data to the feature extraction module and the data analysis module;

[0122] Feature extraction module, which is used to extract features from the received data according to the required requirements, generate advertising feature information according to the content of the advertising product, extract the user's age information and regional information according to the registration information of the user's login ID, and transmit the extracted feature information to the data analysis module;

[0123] Data analysis module: The data analysis module is used to analyze and process the received data. By collating and analyzing the data from the data collection module and the feature extraction module, it generates thread fluctuation performance information, behavior difference value, advertising acceptance, advertising-induced search probability, advertising effect evaluation value, advertising audience information, advertising audience portrait and user delivery effect threshold, and transmits the data to the intelligent monitoring module and the effect display module;

[0124] Intelligent monitoring module, which is used to compare the advertising effect evaluation value transmitted by the data analysis module with the user delivery effect threshold, monitor whether the advertising effect evaluation value meets the standard, and transmit the monitoring result to the effect display module;

[0125] The effect display module is used to analyze and organize the received data and display the advertising monitoring results.

[0126] Specifically, the data collection module includes:

[0127] A first collection unit, the first collection unit is used to establish a data connection with a cloud video platform server and obtain thread information from the cloud video platform server;

[0128] The second collecting unit is used to establish a communication connection with the advertiser and obtain the advertisement information from the advertiser.

[0129] Specifically, the feature extraction module includes:

[0130] A first extraction unit, the first extraction unit is used to extract features from the received advertisement information, generate advertisement product content and advertisement duration, and generate advertisement feature information according to the advertisement product content;

[0131] The second extraction unit is used to extract data features of the received user ID registration information according to age and region to generate an advertising audience portrait.

[0132] Specifically, the data analysis module includes:

[0133] A first analysis unit, the first analysis unit is used to analyze the received thread fluctuation performance information to generate execution state fluctuation performance information, thread number fluctuation performance information and resource occupancy fluctuation performance information;

[0134] A second analysis unit, the second analysis unit is used to analyze the resource occupancy fluctuation time according to the advertisement duration to determine the advertisement time period;

[0135] A third analysis unit, the third analysis unit is used to analyze the thread quantity fluctuation frequency difference and the resource occupancy fluctuation frequency difference by taking the execution state fluctuation frequency difference as a reference variable, and obtain the thread quantity fluctuation correlation coefficient and the resource occupancy fluctuation correlation coefficient respectively;

[0136] The fourth analysis unit and the third analysis unit are used to analyze the advertisement acceptance matrix and the user influence state transition probability matrix through the specific calculation formula of the advertisement induced search probability, and generate the advertisement induced search probability.

[0137] In summary, the advantages of the present invention are:

[0138] It can effectively obtain user behavior information based on the thread data fluctuations in the cloud video platform server. By analyzing the user's behavioral motivations, the evaluation results of advertising effects are more accurate, reducing the difference between monitoring results and actual advertising effects, and ensuring that advertisers can have a clearer understanding of advertising effects.

[0139] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. An intelligent monitoring method for advertising delivery effect based on cloud video data analysis, characterized in that: include: Obtain and analyze cloud video platform server data to generate advertising feature information and user behavior information; Based on user behavior information, obtain behavior difference values, combine with advertising feature information, and generate advertising acceptance; Based on the cloud video platform, historical data of advertising delivery is obtained to generate the probability of advertising-induced searches; Generate advertising effect evaluation value and advertising audience information based on advertising acceptance, behavioral difference value and advertising-induced search probability; Classify advertising audience information and generate advertising audience portraits; Based on historical advertising data, analyze the probability of advertising-induced searches and advertising audience portraits, and set user delivery effect thresholds; Based on the user delivery effect threshold, the advertising effect evaluation value is analyzed to determine whether the advertising effect evaluation value is greater than the user delivery effect threshold. If so, the advertising content is optimized according to the advertising audience portrait to maintain the audience's freshness and attention to the advertisement. If not, the advertising delivery is adjusted according to the advertising audience portrait.

2. According to claim 1, a method for intelligently monitoring advertising delivery effects based on cloud video data analysis is characterized in that: The generating of advertisement feature information and user behavior information specifically includes: Processing the cloud video platform server data to obtain server thread occupancy and advertising information, wherein the advertising information includes advertising product content and advertising duration; Generate advertisement feature information according to the advertisement product content; Obtain the user's login ID on the cloud video platform, bind the user's login ID to the server thread based on the cloud video server data, and obtain the user-associated thread; Analyze the server thread occupancy according to the user-associated thread to obtain thread fluctuation performance information, wherein the thread fluctuation performance information includes execution state fluctuation performance information, thread quantity fluctuation performance information and resource occupancy fluctuation performance information; Generate user behavior information based on thread fluctuation performance information; Through the execution status fluctuation performance information of the user-associated thread, it is determined whether the user has paused the video playback; through the thread number fluctuation performance information of the user-associated thread, it is determined whether the user has interacted with the video; through the resource usage fluctuation performance information of the user-associated thread, it is determined whether the user has downloaded the video.

3. According to claim 2, a method for intelligently monitoring advertising delivery effects based on cloud video data analysis is characterized in that: The obtaining of the behavior difference value and combining it with the advertisement feature information to generate the advertisement acceptance specifically includes: Obtain thread fluctuation time based on cloud video platform server data and thread fluctuation performance information; Analyze resource usage fluctuations based on ad duration and determine ad time slots; Divide the thread fluctuation time according to the advertising period, and generate the thread occupancy information of the pre-ad period and the post-ad period in combination with the server thread occupancy status; Taking three minutes as a time period, analyzing the execution state fluctuation performance information, the thread number fluctuation performance information and the resource occupancy fluctuation performance information, and obtaining the execution state fluctuation frequency information, the thread number fluctuation frequency information and the resource occupancy fluctuation frequency information; Analyze the thread occupancy information of the pre-ad period and the post-ad period from the perspectives of execution status, thread number, and resource occupancy fluctuations, and generate execution status fluctuation frequency difference, thread number fluctuation frequency difference, and resource occupancy fluctuation frequency difference respectively; Based on the Pearson correlation coefficient calculation formula, the execution state fluctuation frequency difference is used as the benchmark variable, and the thread number fluctuation frequency difference and resource occupancy fluctuation frequency difference are analyzed to obtain the thread number fluctuation correlation coefficient and resource occupancy fluctuation correlation coefficient respectively; The behavior difference value is obtained by obtaining the ratio of the correlation coefficient of thread quantity fluctuation and the correlation coefficient of resource occupancy fluctuation; Generate an advertising perception table based on historical advertising data; Substitute the advertising feature information into the advertising perception table to obtain the standard difference value, combine it with the behavioral difference value, generate advertising acceptance, and calculate the advertising acceptance state transition probability of different behavioral difference values ​​to establish an advertising acceptance matrix.

4. The method for intelligently monitoring advertising delivery effects based on cloud video data analysis according to claim 3 is characterized in that: The generating of the advertisement-induced search probability specifically includes: Organize historical data on advertising, divide it by advertising acceptance, and generate user impact status information; According to the user influence status information, the historical data of advertising delivery is analyzed, the user status probabilities with different acceptance levels are calculated, and the user influence status transition probability matrix is ​​generated; Analyze the advertisement acceptance matrix and the user influence state transition probability matrix to generate advertisement-induced search probability; The specific calculation formula for the probability of advertisement-induced search is: P[s k+1 |s k ]=P[s1|s2,s3,s4]P[v|v1,v2,v3]; In the formula, P[s k+1 |s k ] is the probability of advertisement-induced search, s k+1 is the impact state of the k+1th user, s k is the kth user influence state, s1, s2, s3, s4 are user influence states, v is the current advertising acceptance state, v1, v2, v3 are advertising acceptance states, P[s1|s2,s3,s4] is the user influence state transition probability, and P[v|v1,v2,v3] is the advertising acceptance state transition probability.

5. According to claim 4, a method for intelligently monitoring advertising delivery effects based on cloud video data analysis is characterized in that: The generating of the advertising effect evaluation value and the advertising audience information specifically includes: Obtain the registration information of the user login ID, classify the user information based on the advertising acceptance, obtain the average advertising acceptance of different user groups, and generate advertising audience information; Obtain the total number of ad viewers, and combine it with ad audience information to determine the distribution of different user groups in the total number of ad viewers; The advertising effect evaluation value is generated by taking a weighted sum of the advertising-induced search probability corresponding to the average advertising acceptance of each user group and the distribution of each user group in the total number of advertisement viewers.

6. The method for intelligently monitoring the advertising effect based on cloud video data analysis according to claim 5 is characterized in that: The setting of user delivery effect threshold specifically includes: According to the advertising audience portrait, the historical data of the same type of advertising is classified according to age information and regional information, and the age advertising effect data and regional advertising effect data are generated; The age-based delivery effect data and the regional delivery effect data are collated and analyzed respectively to obtain the age-based delivery effect peak data, age-based delivery effect valley data, regional delivery effect peak data, and regional delivery effect valley data; The age delivery effect peak data and the age delivery effect valley data are averaged and summed to generate the age delivery effect threshold, and the region delivery effect peak data and the region delivery effect valley data are averaged and summed to generate the region delivery effect threshold; According to the registration information of the user browsing the advertisement, the corresponding age delivery effect threshold and regional delivery effect threshold are obtained, and the average value is calculated to generate the user delivery effect threshold.

7. An intelligent monitoring system for advertising delivery effect based on cloud video data analysis, applicable to the monitoring method according to any one of claims 1 to 6, characterized in that: Specifically include: A data collection module, which is used to establish a data connection with the cloud video platform server, obtain cloud video platform server data, obtain advertising information from the advertiser, and transmit the collected information data to the feature extraction module and the data analysis module; A feature extraction module, which is used to extract features from the received data according to the required requirements, generate advertisement feature information according to the advertisement product content, extract the user's age information and region information according to the registration information of the user login ID, and transmit the extracted feature information to the data analysis module; A data analysis module, which is used to analyze and process the received data, and to generate thread fluctuation performance information, behavior difference value, advertisement acceptance, advertisement-induced search probability, advertisement effect evaluation value, advertisement audience information, advertisement audience portrait and user delivery effect threshold by collating and analyzing the data of the data collection module and the feature extraction module, and transmit the data to the intelligent monitoring module and the effect display module; An intelligent monitoring module, which is used to compare the advertising effect evaluation value transmitted by the data analysis module with the user delivery effect threshold, monitor whether the advertising effect evaluation value meets the standard, and transmit the monitoring result to the effect display module; The effect display module is used to analyze and organize the received data and display the advertising monitoring results.

8. The intelligent monitoring system for advertising delivery effect based on cloud video data analysis according to claim 7 is characterized in that: The data collection module specifically includes: A first collecting unit, wherein the first collecting unit is used to establish a data connection with a cloud video platform server and obtain thread information from the cloud video platform server; The second collecting unit is used to establish a communication connection with the advertiser and obtain the advertisement information from the advertiser.

9. The intelligent monitoring system for advertising delivery effect based on cloud video data analysis according to claim 8 is characterized in that: The feature extraction module specifically includes: A first extraction unit, the first extraction unit is used to extract features from the received advertisement information, generate advertisement product content and advertisement duration, and generate advertisement feature information according to the advertisement product content; The second extraction unit is used to extract data features of the received user ID registration information according to age and region to generate an advertising audience portrait.

10. The intelligent monitoring system for advertising delivery effect based on cloud video data analysis according to claim 9 is characterized in that: The data analysis module specifically includes: A first analysis unit, the first analysis unit is used to analyze the received thread fluctuation performance information to generate execution state fluctuation performance information, thread number fluctuation performance information and resource occupancy fluctuation performance information; A second analysis unit, the second analysis unit is used to analyze the resource occupancy fluctuation time according to the advertisement duration to determine the advertisement time period; A third analysis unit, the third analysis unit is used to analyze the thread quantity fluctuation frequency difference and the resource occupancy fluctuation frequency difference by taking the execution state fluctuation frequency difference as a reference variable, and obtain the thread quantity fluctuation correlation coefficient and the resource occupancy fluctuation correlation coefficient respectively; The fourth analysis unit, the third analysis unit is used to analyze the advertisement acceptance matrix and the user influence state transition probability matrix through the specific calculation formula of the advertisement induced search probability, and generate the advertisement induced search probability.

Images