Artificial intelligence advertisement marketing pushing method based on Internet

Abstract

The invention discloses an Internet-based artificial intelligence advertisement marketing pushing method, and particularly relates to the technical field of advertisement marketing, comprising the steps of analyzing search hot words and hot topics by using natural language processing and text analysis technologies, determining feature trend vocabularies of an Internet platform by counting the occurrence frequency of the vocabularies, and pushing the feature trend vocabularies to the Internet platform; the method comprises the following steps: determining feature trend vocabularies in an internet platform and feature trend vocabularies of a pushed advertisement in real time, determining trend change information of the pushed advertisement by using a knowledge graph technology and an emotion analysis technology, and determining the advertisement push flow through a relationship between the flow size of the pushed advertisement push flow and the advertisement click rate in the internet platform by using a correlation analysis method. According to the method and the system, the excessive input of low-efficiency advertisements can be avoided, and the advertisement flow pushing strategy is optimized in real time according to the market and user feedback, so that the maximization of the advertisement putting effect is realized.

Description

Technical Field

[0001] The present invention relates to the field of advertising and marketing technology, and more specifically, to an artificial intelligence advertising and marketing push method based on the Internet. Background Art

[0002] With the rapid development of the Internet, the advertising and marketing industry has ushered in unprecedented opportunities and challenges. Especially on the Internet platform, advertising push has become an important business model. Existing advertising push technology mainly relies on traditional keyword matching, user behavior analysis and traffic optimization algorithms. However, in the face of rapid market changes and diversified user interests, traditional methods are difficult to effectively adjust advertising push strategies, and it is not easy to accurately identify target users during push, resulting in waste of advertising traffic and budget.

[0003] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an Internet-based artificial intelligence advertising marketing push method to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An artificial intelligence advertising marketing push method based on the Internet specifically comprises the following steps:

[0007] S1: Analyze hot search words and hot topics by using natural language processing and text analysis technology, and determine the characteristic trend words of the Internet platform by counting the frequency of occurrence of words;

[0008] S2: By determining the characteristic trend words in the Internet platform and the characteristic trend words of the pushed advertisements in real time, using the knowledge graph technology and sentiment analysis technology, the trend change information of the pushed advertisements is determined;

[0009] S3: By using the relationship between the traffic volume of push ads and the number of ad clicks on the Internet platform, a correlation analysis method is used to determine the popularity potential information of push ads;

[0010] S4: Comprehensively analyze the heat potential information and heat potential information of the push advertisements to determine whether to continue to support push traffic for the push advertisements.

[0011] In a preferred embodiment, determining the characteristic trend words of the Internet platform includes:

[0012] Capture hot search words and hot topics on the Internet platform in real time, extract characteristic trend words on the Internet platform through text analysis technology, set frequency thresholds by counting the frequency of occurrence of words in the captured hot search words and hot topics, and determine words with a frequency greater than the threshold as characteristic trend words.

[0013] In a preferred embodiment, the heat potential information of the push advertisement is determined

[0014] The trend change information of the pushed advertisement is represented by the hotspot correlation coefficient and the hotspot index trend coefficient;

[0015] The logic for obtaining the hotspot correlation coefficient is as follows: construct a knowledge graph based on characteristic trend words in the Internet platform, wherein the nodes in the knowledge graph represent entities, the entities are various trend characteristic words, the edges in the knowledge graph represent the correlation between entities, and the correlation is the weight between entities;

[0016] Based on the historical records of the Internet platform, the co-occurrence frequency between entities is determined, and the weights between entities are calculated. The calculation formula is: Where QZ(A,B) is the weight between entity A and entity B, CS(A,B) is the number of times entity A and entity B appear together as characteristic trend words in the history records of the Internet platform, ∑ C∈all terms CS(A,C) is the sum of the co-occurrence times of entity A and all other trend feature words;

[0017] Determine the Internet platform characteristic trend vocabulary set, and express the Internet platform characteristic trend vocabulary set as: LW i =[LW1,LW2,LW3,……,LW I ], determine the vocabulary of the push advertisement through the word segmentation technology, obtain the characteristic trend vocabulary of the push advertisement, determine the characteristic trend vocabulary set of the push advertisement, and the characteristic trend vocabulary set of the push advertisement is expressed as: QS n =[QS1,QS2,QS3,……,QS N ];

[0018] Calculate the hotspot correlation coefficient, the calculation formula is: Among them, GL rd is the hotspot correlation coefficient.

[0019] In a preferred embodiment, the hotspot index trend coefficient includes:

[0020] The logic for obtaining the trend coefficient of the hot index is as follows: determine the vocabulary of the push advertisement comment by word segmentation technology, determine the sentiment score of each vocabulary of the push advertisement comment by using the sentiment dictionary, determine the total sentiment score of the push advertisement comment, and mark the total sentiment score of each push advertisement comment as: DFm , where m = 1, 2, 3, ..., M, M is a positive integer, and m is the number of the pushed advertisement comment;

[0021] Calculate the hot index trend coefficient of the push advertisement. The calculation formula is: Among them, ZS qs is the hot index trend coefficient of the pushed advertisement, DZ m The number of likes for each push ad comment.

[0022] In a preferred embodiment, determining the popularity potential information of the pushed advertisement includes:

[0023] The potential information of the popularity of the push advertisement is expressed through the traffic anonymity coefficient;

[0024] The logic for obtaining the traffic anonymity coefficient is as follows: set a monitoring time period, determine the push traffic size of each push advertisement within the monitoring time period, and mark the push traffic size of each round of push advertisement within the monitoring time period as: LL k , where k = 1, 2, 3, ..., K, K is a positive integer, and k is the number of each delivery flow in the monitoring time period;

[0025] Determine the increase in the number of clicks on the push ads after each push within the monitoring period, and mark the increase in the number of clicks on the push ads after each push within the monitoring period as: ZJ k ;

[0026] Calculate the traffic anonymity coefficient using the following formula: Among them, XG is the flow anonymity coefficient, is the average value of each push traffic during the monitoring period. It is the average increase in the number of ad clicks each time during the monitoring period.

[0027] In a preferred embodiment, the heat potential information and heat potential information of the pushed advertisement are comprehensively analyzed, including:

[0028] Through comprehensive analysis of the trend change information of push ads and the heat potential information of push ads, the hot spot correlation coefficient, hot spot index trend coefficient and traffic anonymity coefficient are weighted and calculated to build a push flow evaluation model and generate a push flow evaluation coefficient. The calculation formula of the push flow evaluation coefficient is: Among them, PG tl is the flow evaluation coefficient, α1, α2, and α3 are the proportional coefficients of the hotspot correlation coefficient, the hotspot index trend coefficient, and the traffic anonymity coefficient, respectively. α1, α2, and α3 are all greater than 0.

[0029] In a preferred implementation, determining whether to continue to support push traffic for push advertisements includes:

[0030] Set a push flow evaluation coefficient threshold and compare the push flow evaluation coefficient of the pushed advertisement with the push flow evaluation coefficient threshold;

[0031] If the push traffic evaluation coefficient of the push advertisement is greater than the push traffic evaluation coefficient threshold, the push traffic of the push advertisement will continue to be supported;

[0032] If the push flow evaluation coefficient of the push advertisement is less than the push flow evaluation coefficient threshold, a warning signal is generated, and new push flows for the push advertisement are stopped. The users are further analyzed through artificial intelligence technology to identify different user groups, and the push flow evaluation coefficients of the push advertisements in different user groups are determined. The push flow evaluation coefficients of different user groups are compared with the push flow evaluation coefficient threshold, and push flow support is continuously provided to user groups whose push flow evaluation coefficient is greater than the push flow evaluation coefficient threshold until the push flow evaluation coefficient of the push advertisement is less than the push flow evaluation coefficient threshold.

[0033] Technical effects and advantages of the present invention:

[0034] The present invention uses natural language processing and text analysis technology to analyze search hot words and hot topics, determines the characteristic trend vocabulary of the Internet platform, uses knowledge graph technology and sentiment analysis technology to determine the heat potential information of push advertisements, and uses correlation analysis method to determine the heat potential information of push advertisements, conducts comprehensive analysis on the heat potential information and heat potential information of push advertisements, and determines whether to continue to support push traffic for push advertisements. The present invention helps to avoid excessive investment in inefficient advertisements, optimizes the advertisement push strategy in real time according to market and user feedback, thereby maximizing the effect of advertising delivery. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0036] Figure 1 The present invention is a flowchart of an Internet-based artificial intelligence advertising marketing push method. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not 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.

[0038] Example 1

[0039] Figure 1 The present invention is a flowchart of an Internet-based artificial intelligence advertising marketing push method, which specifically includes the following steps:

[0040] S1: Analyze hot search words and hot topics by using natural language processing and text analysis technology, and determine the characteristic trend words of the Internet platform by counting the frequency of occurrence of words;

[0041] S2: By determining the characteristic trend words in the Internet platform and the characteristic trend words of the pushed advertisements in real time, using the knowledge graph technology and sentiment analysis technology, the trend change information of the pushed advertisements is determined;

[0042] S3: By using the relationship between the traffic volume of push ads and the number of ad clicks on the Internet platform, a correlation analysis method is used to determine the popularity potential information of push ads;

[0043] S4: Comprehensively analyze the heat potential information and heat potential information of the push advertisements to determine whether to continue to support push traffic for the push advertisements.

[0044] Ad push is a dynamic optimization process based on user data, ad content and advertiser needs. By using technologies such as big data, machine learning and real-time bidding, ad push can achieve accurate targeted delivery, personalized recommendations and effect optimization, thereby improving the conversion rate of ads and the return on investment of advertisers. By combining characteristic vocabulary trends for ad push, it can capture the fluctuations and popular trends of user interests in real time, ensure the high relevance and timeliness of ad content, and thus improve the advertising effect, including:

[0045] Characteristic trend words refer to the changing trends of the search frequency, social discussion volume, web page click volume, etc. of certain specific words or keywords within a certain period of time. These words can reflect the interests and needs of users or the hot spots of a certain event.

[0046] Use natural language processing (NLP) and text analysis technology to track the popularity changes of specific words or phrases in real time, determine which words are becoming hot topics, perform cluster analysis on frequently appearing keywords, and identify potential hot words;

[0047] Based on the analyzed hot words or hot topics, we customize the related advertising content, create advertisements that match the characteristic vocabulary trends through automated advertising generation technology, and push the advertisements containing the characteristic vocabulary;

[0048] Use stream processing frameworks (such as Apache Kafka, Apache Flink, etc.) for real-time data analysis to quickly identify and respond to trend changes in feature vocabulary, and use big data technology to analyze massive user behavior data, search data, and social media data to extract valuable trend information.

[0049] By real-time determining the characteristic trend words in the Internet platform and the characteristic trend words of the push ads, using knowledge graph technology and sentiment analysis technology, the trend change information of the push ads is determined, and the trend change information of the push ads is represented by the hot spot correlation coefficient and the hot spot index trend coefficient.

[0050] Among them, the advantages of the hot spot correlation coefficient are:

[0051] The hotspot correlation coefficient can capture the characteristic trend words of the Internet platform (such as hot topics and popular keywords), process the advertising content through natural language processing (NLP), and further use the knowledge graph to determine the correlation between the characteristic trend words of the Internet platform and the advertisement;

[0052] The hot topic relevance coefficient can timely capture the hot topics or keywords that users are concerned about by analyzing the trending words on the Internet platform, so that the advertising push system can push advertising content that is highly consistent with the user's interests at the right time, thereby improving the relevance of the advertisement;

[0053] By using the knowledge graph to analyze the semantic relationship between advertisements and hot trends, the advertising system can accurately deliver advertisements to user groups that are relevant to the trend and have a high level of interest, thus avoiding blind delivery and reducing resource waste.

[0054] By using the hotspot correlation coefficient, the advertising system can avoid pushing irrelevant advertisements to users, thereby avoiding invalid traffic consumption.

[0055] The acquisition logic of the hot spot correlation coefficient is: real-time capture of search hot words and hot topics in the Internet platform, extraction of characteristic trend words in the Internet platform through text analysis technology, statistical appearance frequency of the characteristic trend words in the captured search hot words and hot topics, setting a frequency threshold, and determining words with a frequency greater than the frequency threshold as characteristic trend words;

[0056] Construct a knowledge graph based on the characteristic trend words in the Internet platform, where the nodes in the knowledge graph represent entities, the entities are various trend characteristic words, and the edges in the knowledge graph represent the correlation between entities, and the correlation is the weight between entities;

[0057] It should be noted that hot search words and hot topics are changing dynamically, so the construction of the knowledge graph is a continuous optimization process. By continuously capturing different trend feature words in real time, a knowledge graph of feature trend words based on the historical records of the Internet platform is formed.

[0058] Based on the historical records of the Internet platform, the co-occurrence frequency between entities is determined, and the weights between entities are calculated. The calculation formula is: Where QZ(A,B) is the weight between entity A and entity B, CS(A,B) is the number of times entity A and entity B appear together as characteristic trend words in the history records of the Internet platform, ∑ C∈all terms CS(A,C) is the sum of the co-occurrence times of entity A and all other trend feature words;

[0059] Determine the Internet platform characteristic trend vocabulary set, and express the Internet platform characteristic trend vocabulary set as: LW i =[LW1,LW2,LW3,……,LW I ], determine the vocabulary of the push advertisement through the word segmentation technology, obtain the characteristic trend vocabulary of the push advertisement, determine the characteristic trend vocabulary set of the push advertisement, and the characteristic trend vocabulary set of the push advertisement is expressed as: QS n =[QS1,QS2,QS3,……,QS N ];

[0060] Calculate the hotspot correlation coefficient, the calculation formula is: Among them, GL rd is the hotspot correlation coefficient.

[0061] It can be seen from the formula that the larger the hot spot correlation coefficient is, the higher the correlation coefficient is. It usually means that the characteristic trend words on the Internet platform (such as popular topics, popular keywords) and the characteristic words in the push advertisements (keywords and descriptions in the advertisements, etc.) have a higher semantic match, which means that the traffic of the push advertisements can be increased.

[0062] Among them, the advantages of the hotspot index trend coefficient are:

[0063] Through sentiment lexicon and sentiment analysis technology, users’ emotional tendencies (such as positive, negative or neutral) in ad comments can be accurately identified, which enables advertising platforms to gain in-depth understanding of users’ reactions to ads and adjust ad content or push strategies based on emotional feedback;

[0064] By analyzing user emotions, advertising platforms can enhance ad exposure based on positive emotional comments and avoid the impact of negative emotions, ultimately improving advertising effectiveness and user satisfaction;

[0065] Advertising platforms can use sentiment analysis to avoid pushing unwelcome or negatively charged ads to users, reduce advertising waste, and ensure that advertising budgets are spent accurately on efficient advertising push.

[0066] The logic for obtaining the trend coefficient of the hot index is as follows: determine the vocabulary of the push advertisement comment by word segmentation technology, determine the sentiment score of each vocabulary of the push advertisement comment by using the sentiment dictionary, determine the total sentiment score of the push advertisement comment, and mark the total sentiment score of each push advertisement comment as: DF m , where m = 1, 2, 3, ..., M, M is a positive integer, and m is the number of the pushed advertisement comment;

[0067] It should be noted that for Chinese text in advertising comments, commonly used tools include jieba (for Chinese word segmentation) or word segmentation methods such as BERT based on deep learning. By assigning a sentiment score to each word, the total sentiment score of the pushed advertising comments is the sum of the sentiment scores of each word in the pushed advertising comments.

[0068] Calculate the hot index trend coefficient of the push advertisement. The calculation formula is: Among them, ZS qs is the hot index trend coefficient of the pushed advertisement, DZ m The number of likes for each push ad comment.

[0069] From the formula, we can see that the larger the trend coefficient of the hot index is, the more popular the content of the push advertisement is among the public, which indicates that the advertisement has stronger exposure opportunities, user engagement, interaction possibilities and market potential, indicating that the traffic of push advertisements can be increased.

[0070] Through the relationship between the traffic size of push ads and the number of ad clicks on the Internet platform, the correlation analysis method is used to determine the heat potential information of the push ads, and the heat potential information of the push ads is represented by the traffic anonymity coefficient.

[0071] Among them, the advantages of the traffic anonymity coefficient are:

[0072] The traffic anonymity coefficient can effectively capture the mismatch between traffic and clicks. For example, even if the traffic pushed increases, but the clicks do not increase accordingly, the traffic anonymity deviation coefficient will increase. This deviation may reflect that the advertising content is not well matched with the target audience, or that the traffic source is not accurate. It can timely discover and correct the phenomenon of inflated traffic;

[0073] The traffic anonymity coefficient can clearly reveal whether the effect of advertising push has reached the expected level. If the traffic anonymity coefficient is low, specific optimization measures can be taken, such as adjusting the advertising content, accurately positioning the target audience, and improving the advertising display method.

[0074] The logic for obtaining the traffic anonymity coefficient is as follows: set a monitoring time period, determine the push traffic size of each push advertisement within the monitoring time period, and mark the push traffic size of each round of push advertisement within the monitoring time period as: LL k , where k = 1, 2, 3, ..., K, K is a positive integer, and k is the number of each delivery flow in the monitoring time period;

[0075] Determine the increase in the number of clicks on the push ads after each push within the monitoring period, and mark the increase in the number of clicks on the push ads after each push within the monitoring period as: ZJ k ;

[0076] Calculate the traffic anonymity coefficient using the following formula: Among them, XG is the flow anonymity coefficient, is the average value of each push traffic during the monitoring period. The average value of the increase in clicks on each ad push during the monitoring period;

[0077] It should be noted that the monitoring time period is a specific time period used to analyze the relationship between the traffic size of push ads and the number of ad clicks. The monitoring time period is set by professional staff. The greater the push traffic of a push ad, the greater the corresponding ad clicks. When the ad clicks do not change significantly due to the push traffic of the push ad, it means that the push ad has lost its push potential and it is necessary to stop pushing the ad.

[0078] From the formula, we can see that the larger the traffic anonymity coefficient is, the stronger the correlation between traffic and clicks is. When the push traffic is larger, the clicks on the push ads are larger. Conversely, the smaller the traffic anonymity coefficient is, the increase in clicks is not significant or may even be negatively correlated when traffic increases, indicating that the push traffic may not be effectively converted into clicks. This may be due to factors such as advertising content and target audience matching, or the way the ads are displayed does not attract user clicks, and it is necessary to reduce the push traffic for push ads.

[0079] Through comprehensive analysis of the trend change information of push ads and the heat potential information of push ads, the hot spot correlation coefficient, hot spot index trend coefficient and traffic anonymity coefficient are weighted and calculated to build a push flow evaluation model and generate a push flow evaluation coefficient. The calculation formula of the push flow evaluation coefficient is: Among them, PG tl is the flow evaluation coefficient, α1, α2, and α3 are the proportional coefficients of the hotspot correlation coefficient, the hotspot index trend coefficient, and the traffic anonymity coefficient, respectively. α1, α2, and α3 are all greater than 0.

[0080] It can be seen from the formula that the larger the hotspot correlation coefficient, the hotspot index trend coefficient and the traffic anonymity coefficient, the larger the push flow evaluation coefficient, which means that push advertising can increase push flow to users. Conversely, the smaller the hotspot correlation coefficient, the hotspot index trend coefficient and the traffic anonymity coefficient, the smaller the push flow evaluation coefficient, which means that push advertising should reduce push flow to users.

[0081] A push flow evaluation coefficient threshold is set, and the push flow evaluation coefficient of the push advertisement is compared with the push flow evaluation coefficient threshold. If the push flow evaluation coefficient of the push advertisement is greater than the push flow evaluation coefficient threshold, then the push flow support for the push advertisement is continued. If the push flow evaluation coefficient of the push advertisement is less than the push flow evaluation coefficient threshold, a warning signal is generated, and new push flows for the push advertisement are stopped. Through artificial intelligence technology, users are further analyzed, different user groups are identified, and the push flow evaluation coefficients of push advertisements in different user groups are determined. The push flow evaluation coefficients of different user groups are compared with the push flow evaluation coefficient threshold. Push flow support is continued for user groups whose push flow evaluation coefficient is greater than the push flow evaluation coefficient threshold until the push flow evaluation coefficient of the push advertisement is less than the push flow evaluation coefficient threshold.

[0082] The present invention uses natural language processing and text analysis technology to analyze search hot words and hot topics, determines the characteristic trend vocabulary of the Internet platform, uses knowledge graph technology and sentiment analysis technology to determine the trend change information of push advertisements, and uses correlation analysis method to determine the heat potential information of push advertisements. The heat potential information and heat potential information of push advertisements are comprehensively analyzed to determine whether to continue to support push traffic for push advertisements. The present invention helps to avoid excessive investment in inefficient advertisements, optimizes the advertisement push strategy in real time according to market and user feedback, thereby maximizing the effect of advertising delivery.

[0083] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0084] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0085] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0086] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0087] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0088] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An artificial intelligence advertising marketing push method based on the Internet, characterized in that: The specific steps include: S1: Analyze hot search words and hot topics by using natural language processing and text analysis technology, and determine the characteristic trend words of the Internet platform by counting the frequency of occurrence of words; S2: By determining the characteristic trend words in the Internet platform and the characteristic trend words of the pushed advertisements in real time, using the knowledge graph technology and sentiment analysis technology, the trend change information of the pushed advertisements is determined; S3: By using the relationship between the traffic volume of push ads and the number of ad clicks on the Internet platform, a correlation analysis method is used to determine the popularity potential information of push ads; S4: Comprehensively analyze the heat potential information and heat potential information of the push advertisements to determine whether to continue to support push traffic for the push advertisements.

2. The method for pushing advertising marketing based on the Internet by artificial intelligence according to claim 1, characterized in that: Identify the characteristic trend words of the Internet platform, including: Capture hot search words and hot topics on the Internet platform in real time, extract characteristic trend words on the Internet platform through text analysis technology, set frequency thresholds by counting the frequency of occurrence of words in the captured hot search words and hot topics, and determine words with a frequency greater than the threshold as characteristic trend words.

3. The method for pushing advertising marketing based on the Internet by artificial intelligence according to claim 2, characterized in that: Determine the popularity potential of push ads The trend change information of the pushed advertisement is represented by the hotspot correlation coefficient and the hotspot index trend coefficient; The logic for obtaining the hotspot correlation coefficient is as follows: construct a knowledge graph based on characteristic trend words in the Internet platform, wherein the nodes in the knowledge graph represent entities, the entities are various trend characteristic words, the edges in the knowledge graph represent the correlation between entities, and the correlation is the weight between entities; Based on the historical records of the Internet platform, the co-occurrence frequency between entities is determined, and the weights between entities are calculated. The calculation formula is: Where QZ(A,B) is the weight between entity A and entity B, CS(A,B) is the number of times entity A and entity B appear together as characteristic trend words in the history records of the Internet platform, ∑ C∈all terms CS(A,C) is the sum of the co-occurrence times of entity A and all other trend feature words; Determine the Internet platform characteristic trend vocabulary set, and express the Internet platform characteristic trend vocabulary set as: LW i =[LW1,LW2,LW3,……,LW I ], determine the vocabulary of the push advertisement through the word segmentation technology, obtain the characteristic trend vocabulary of the push advertisement, determine the characteristic trend vocabulary set of the push advertisement, and the characteristic trend vocabulary set of the push advertisement is expressed as: QS n =[QS1,QS2,QS3,……,QS N ]; Calculate the hotspot correlation coefficient, the calculation formula is: Among them, GL rd is the hotspot correlation coefficient.

4. The method for pushing advertising marketing based on the Internet by artificial intelligence according to claim 3, characterized in that: Hotspot index trend coefficient, including: The logic for obtaining the trend coefficient of the hot index is as follows: determine the vocabulary of the push advertisement comment by word segmentation technology, determine the sentiment score of each vocabulary of the push advertisement comment by using the sentiment dictionary, determine the total sentiment score of the push advertisement comment, and mark the total sentiment score of each push advertisement comment as: DF m , where m = 1, 2, 3, ..., M, M is a positive integer, and m is the number of the pushed advertisement comment; Calculate the hot index trend coefficient of the push advertisement. The calculation formula is: Among them, ZS qs is the hot index trend coefficient of the pushed advertisement, DZ m The number of likes for each push ad comment.

5. The method for pushing advertising marketing based on the Internet by artificial intelligence according to claim 4, characterized in that: Determine the potential popularity of the push ads, including: The potential information of the popularity of the push advertisement is expressed through the traffic anonymity coefficient; The acquisition logic of the traffic anonymity coefficient is: set a monitoring time period, determine the push traffic size of each push advertisement within the monitoring time period, and mark the push traffic size of each round of push advertisement within the monitoring time period as: LL k , where k = 1, 2, 3, ..., K, K is a positive integer, and k is the number of each delivery flow in the monitoring time period; Determine the increase in the number of clicks on the push ads after each push within the monitoring period, and mark the increase in the number of clicks on the push ads after each push within the monitoring period as: ZJ k ; Calculate the traffic anonymity coefficient using the following formula: Among them, XG is the flow anonymity coefficient, is the average value of each push traffic during the monitoring period. It is the average increase in the number of ad clicks each time during the monitoring period.

6. The method for pushing advertising marketing based on the Internet by artificial intelligence according to claim 5, characterized in that: Comprehensively analyze the heat potential information and heat potential information of the pushed advertisements, including: Through comprehensive analysis of the trend change information of push ads and the heat potential information of push ads, the hot spot correlation coefficient, hot spot index trend coefficient and traffic anonymity coefficient are weighted and calculated to build a push flow evaluation model and generate a push flow evaluation coefficient. The calculation formula of the push flow evaluation coefficient is: Among them, PG tl is the flow evaluation coefficient, α1, α2, and α3 are the proportional coefficients of the hotspot correlation coefficient, the hotspot index trend coefficient, and the traffic anonymity coefficient, respectively. α1, α2, and α3 are all greater than 0.

7. The method for pushing advertising marketing based on the Internet according to claim 6, characterized in that: Determine whether to continue to support push traffic for push ads, including: Set a push flow evaluation coefficient threshold and compare the push flow evaluation coefficient of the pushed advertisement with the push flow evaluation coefficient threshold; If the push traffic evaluation coefficient of the push advertisement is greater than the push traffic evaluation coefficient threshold, the push traffic of the push advertisement will continue to be supported; If the push flow evaluation coefficient of the push advertisement is less than the push flow evaluation coefficient threshold, a warning signal is generated, and new push flows for the push advertisement are stopped. The users are further analyzed through artificial intelligence technology to identify different user groups, and the push flow evaluation coefficients of the push advertisements in different user groups are determined. The push flow evaluation coefficients of different user groups are compared with the push flow evaluation coefficient threshold, and push flow support is continuously provided to user groups whose push flow evaluation coefficient is greater than the push flow evaluation coefficient threshold until the push flow evaluation coefficient of the push advertisement is less than the push flow evaluation coefficient threshold.

Images