An intelligent advertisement analysis management method and system based on blockchain data

Abstract

The application discloses an intelligent advertisement analysis management method and system based on blockchain data, and relates to the technical field of advertisements.The method comprises the following steps: collecting interactive behavior data generated when a user interacts with advertisement content; converting the interactive behavior data into advertisement behavior tags in real time, and performing chain connection with the previous and subsequent advertisement behavior tags through an encryption hash algorithm and storing the same in a blockchain; after the user receives personalized advertisement content, recording the personalized interactive behavior data of the user and the personalized advertisement content in real time and storing the same in the advertisement behavior tag chain, and the advertisement behavior tag chain updates advertisement delivery indexes according to the real-time recorded personalized interactive behavior data.The application can more accurately capture the interest preferences of users by real-time conversion and chain storage of user interactive behavior data, and generates a dynamically updated advertisement behavior tag chain.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of advertising technology, in particular to an intelligent advertising analysis and management method and system based on blockchain data. BACKGROUND

[0002] With the rapid development of the Internet and big data technology, the advertising industry is gradually moving towards intelligence and personalization. Traditional advertising methods mainly rely on manual experience and simple statistical analysis, which is difficult to adapt to changes in user interests and behavior patterns in real time. In recent years, blockchain technology and artificial intelligence models have been widely used in advertising analysis and management, realizing the transparency of the advertising process and efficient processing of data through encryption algorithms and data chain structures.

[0003] However, existing intelligent advertising analysis methods still face some challenges. First, data security and privacy protection is an important issue, and existing systems have the risk of tampering and leakage during data transmission and storage. Second, the degree of personalization of advertising content is not high, making it difficult to accurately capture user interests and preferences, resulting in unsatisfactory advertising results. In addition, existing behavior prediction models need to be improved in real-time performance and accuracy when dealing with large-scale data. SUMMARY

[0004] In view of the above existing problems, the present application is proposed.

[0005] Therefore, the present application provides an intelligent advertising analysis and management method based on blockchain data to solve the problems of advertising data security and privacy protection, personalized advertising content generation, and real-time behavior prediction.

[0006] To solve the above technical problems, the present application provides the following technical solutions:

[0007] In a first aspect, the present application provides an intelligent advertising analysis and management method based on blockchain data, which includes collecting interactive behavior data generated when users interact with advertising content;

[0008] Real-time conversion of interactive behavior data into advertising behavior tags, and chain association with previous and subsequent advertising behavior tags through an encryption hash algorithm and storage in a blockchain;

[0009] Data preprocessing of the advertising behavior tag chain, extraction of advertising delivery indicators, real-time behavior prediction of the advertising delivery indicators using a behavior sequence analysis model, and output of dynamically updated user conversion paths;

[0010] Based on the dynamic updating of the user conversion path, the generative adversarial network is called to generate personalized advertisement content according to the historical interaction behavior data of the user, the version and distribution of the personalized advertisement content are recorded through the advertisement behavior tag chain, and the personalized advertisement content is pushed to the user;

[0011] After the user receives the personalized advertisement content, the personalized interaction behavior data of the user and the personalized advertisement content is recorded in real time and stored in the advertisement behavior tag chain, and the advertisement behavior tag chain updates the advertisement delivery index according to the real-time recorded personalized interaction behavior data.

[0012] As a preferred scheme of the intelligent advertisement analysis management method based on blockchain data, the interaction behavior data includes interaction operation data, device environment data, interest preference data, behavior sequence data, personalized advertisement data and target conversion data.

[0013] As a preferred scheme of the intelligent advertisement analysis management method based on blockchain data, the interaction behavior data is converted into an advertisement behavior tag in real time, and is chain-coupled with the previous and subsequent advertisement behavior tags through an encryption hash algorithm and stored in the blockchain, and the specific steps are as follows,

[0014] The interaction behavior data is normalized by using a standardization function;

[0015] The normalized interaction behavior data is mapped to a high-dimensional semantic space through a nonlinear embedding function to generate a corresponding quantum state probability distribution;

[0016] The eigenvalues of the quantum state probability distribution are described by using a density matrix and are used as semantic features to identify the semantic patterns in the interaction behavior data;

[0017] The identified semantic patterns are subjected to clustering analysis and time correlation analysis to generate advertisement behavior tags corresponding to the interaction behavior data;

[0018] The semantic correlation weights between the advertisement behavior tags are calculated by using a quantum state correlation matrix, and the expression is as follows:

[0019]

[0020] Wherein, A ij represents the semantic correlation weight between the advertisement behavior tags i and j, i and j represent two different advertisement behavior tags, represents the complex conjugate quantum state function of the advertisement behavior tag i at time t, ψ j (t) represents the quantum state function of the advertisement behavior tag j at time t, is a Gaussian time weight function, t0 represents a reference time point of the current behavior event, a represents a time weight factor, and dt represents a small time increment in the integral operation;

[0021] The semantic association weights of all advertising behavior label pairs (i, j) are combined to form a two-dimensional matrix, forming a semantic association matrix;

[0022] Based on the semantic association matrix, a set of all possible advertising behavior label pair paths is constructed

[0023] According to the maximum weight path of the semantic association matrix, a chain structure is constructed to generate an optimal advertising behavior label chain, and the expression is:

[0024]

[0025] wherein, represents the optimal advertising behavior label chain, represents finding the maximum weight path from the set of all possible advertising behavior label pair paths represents summing the semantic association weights of all advertising behavior label pairs (i, j) in the path set;

[0026] On the basis of the optimal advertising behavior label chain , the encrypted hash value of the optimal advertising behavior label chain is generated, and the expression is:

[0027]

[0028] wherein, H k represents the encrypted hash value of the kth optimal advertising behavior label chain, k represents the index variable of the optimal advertising behavior label chain, SHA3 is a secure hash algorithm, and p k (t) represents the quantum state density function of the kth advertising behavior label chain at time t, represents a Gaussian decay factor, and β represents a time weight parameter;

[0029] When a new advertising behavior label is added to the advertising behavior label chain, the semantic association weights of the new advertising behavior label and all advertising behavior labels in the optimal advertising behavior label chain are recalculated, the optimal path is updated, and the encrypted hash value of the new optimal advertising behavior label chain is calculated;

[0030] The semantic association weight of the new advertising behavior label and the encrypted hash value of the updated optimal advertising behavior label chain are stored as new label information in the blockchain, and each advertising behavior label chain is a block;

[0031] ​A semantic index of each advertising behavior label chain is established, and a quantum Bloom filter is used to optimize the query efficiency of the advertising behavior label chain, and the expression is:

[0032]

[0033] Wherein, Q(x) represents the result of the quantum Bloom filter, m represents the number of hash functions in the Bloom filter, z represents the index of the hash function in the Bloom filter, b z represents the Boolean value of the zth hash function, γ z represents the weight parameter of the zth dimension, x represents the input query value, represents the symbol conversion term, represents a weight decay function.

[0034] When the advertising behavior label chain is updated, the corresponding blockchain and the semantic index of the advertising behavior label chain are synchronously updated.

[0035] As a preferred scheme of the intelligent advertising analysis management method based on blockchain data, wherein: the advertising behavior label chain is preprocessed, the advertising delivery indicators are extracted, the behavior sequence analysis model is used to perform real-time behavior prediction on the advertising delivery indicators, and the dynamically updated user conversion path is output, and the specific steps are as follows,

[0036] The advertising behavior label chain is cleaned and standardized, the time sequence of user interaction behavior, click rate and conversion rate are extracted, and the behavior feature matrix containing advertising delivery indicators is generated based on semantic association weight;

[0037] The advertising delivery indicators in the behavior feature matrix are organized into a sliding window sequence in time sequence, and the time interval features between the advertising delivery indicators are calculated to form a behavior sequence containing short-term and long-term dependencies;

[0038] The behavior sequence is input into the behavior sequence analysis model based on LSTM, the historical behavior feature matrix and the current behavior feature matrix are combined, and the next advertising behavior label and its conversion probability of the user are predicted;

[0039] According to the conversion probability, the advertising behavior label is filtered and inserted into the current short-term behavior sequence, and the conversion probability is recorded, and the dynamically updated user conversion path is output.

[0040] As a preferred scheme of the intelligent advertising analysis management method based on blockchain data, wherein: based on the dynamically updated user conversion path, a generative adversarial network is called, personalized advertising content is generated according to the user's historical interaction behavior data, and the specific steps are as follows,

[0041] Based on the user conversion path, the behavior feature matrix and the advertising context are extracted, and a joint feature matrix is combined.

[0042] The joint feature matrix is weighted based on the semantic association weight between the advertisement behavior tags to generate a high-dimensional feature vector;

[0043] The high-dimensional feature vector is input into a bidirectional generative adversarial network, and the generator generates personalized advertisement content, and the discriminator checks the authenticity of the personalized advertisement content and the matching degree with the interaction behavior data;

[0044] Through behavior path analysis, it is verified whether the personalized advertisement content matches the user conversion path, and the relevance and logicality of the content are optimized.

[0045] As a preferred scheme of the intelligent advertisement analysis and management method based on blockchain data, the version and distribution of the personalized advertisement content are recorded through the advertisement behavior tag chain, and the personalized advertisement content is pushed to the user, and the specific steps are as follows,

[0046] Based on the generated personalized advertisement content, the semantic features described by the eigenvalues of the quantum state density matrix are extracted, the unique version identifier is generated by using the encryption hash algorithm, and is stored in association with the advertisement behavior tag chain;

[0047] A distribution record is generated for each advertisement content, the distribution record is stored as a block in the blockchain, and an advertisement distribution record chain is generated;

[0048] The advertisement content version with the highest conversion probability is dynamically matched in combination with the advertisement behavior tag chain and the advertisement distribution record chain of the user;

[0049] The selected advertisement content version is pushed to the user through a content distribution interface.

[0050] As a preferred scheme of the intelligent advertisement analysis and management method based on blockchain data, after the user receives the personalized advertisement content, the real-time personalized interaction behavior data of the user and the personalized advertisement content is recorded and stored in the advertisement behavior tag chain, and the advertisement behavior tag chain updates the advertisement delivery index according to the real-time recorded personalized interaction behavior data, and the specific steps are as follows,

[0051] The SDK integrated by the local application monitors the click, view and conversion data, and collects the personalized interaction behavior data in the form of timestamp;

[0052] The personalized interaction behavior data is encrypted and hashed, the advertisement behavior tags are updated, and they are stored in the blockchain after being semantically associated with the historical advertisement behavior tag chain;

[0053] The click, view and conversion data are extracted from the updated advertisement behavior tag chain, and are fused with the behavior feature matrix to dynamically correct the real-time value of the advertisement delivery index.

[0054] In a second aspect, the present application provides an intelligent advertisement analysis management system based on blockchain data, comprising a data collection module, a storage module, a behavior prediction module, a pushing module and an interaction record module.

[0055] The data collection module is configured to collect interaction behavior data generated when a user interacts with advertisement content.

[0056] The storage module is configured to convert the interaction behavior data into an advertisement behavior tag in real time, and perform chain association with the previous and subsequent advertisement behavior tags through an encryption hash algorithm and store the same in a blockchain.

[0057] The behavior prediction module is configured to perform data preprocessing on the advertisement behavior tag chain, extract advertisement delivery indicators, perform real-time behavior prediction on the advertisement delivery indicators using a behavior sequence analysis model, and output a dynamically updated user conversion path.

[0058] The pushing module is configured to call a generative adversarial network based on the dynamically updated user conversion path, generate personalized advertisement content according to the user's historical interaction behavior data, record the version and distribution of the personalized advertisement content through the advertisement behavior tag chain, and push the personalized advertisement content to the user.

[0059] The interaction record module is configured to record the personalized interaction behavior data between the user and the personalized advertisement content in real time after the user receives the personalized advertisement content and store the same in the advertisement behavior tag chain, and the advertisement behavior tag chain updates the advertisement delivery indicators according to the real-time recorded personalized interaction behavior data.

[0060] In a third aspect, the present application provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, any step of the intelligent advertisement analysis management method based on blockchain data according to the first aspect of the present application is implemented.

[0061] In a fourth aspect, the present application provides a computer readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, any step of the intelligent advertisement analysis management method based on blockchain data according to the first aspect of the present application is implemented.

[0062] The application has the beneficial effects that: the application introduces the blockchain technology, so that the advertising data has the tamper resistance and high security in the transmission and storage process, greatly improving the security and privacy protection of the data. Through real-time conversion and chain storage of user interaction behavior data, a dynamically updated advertising behavior tag chain is generated, so that the interest preferences of the user can be more accurately captured. The generative adversarial network technology is adopted to generate personalized advertising content according to the user historical behavior data, which not only improves the relevance and attractiveness of the advertising, but also can record the personalized interaction behavior data of the user after receiving the advertising content, further optimizing the advertising delivery index and user conversion path. In summary, the application has significant beneficial effects in data security, personalized advertising generation and real-time behavior prediction, and can effectively improve the accuracy and effect of advertising delivery. BRIEF DESCRIPTION OF DRAWINGS

[0063] In order to more clearly illustrate the technical solutions of the embodiments of the application, the drawings needed to be used in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0064] Figure 1 The flowchart of the intelligent advertising analysis management method based on blockchain data in embodiment 1.

[0065] Figure 2 The module diagram of the intelligent advertising analysis management system based on blockchain data in embodiment 1. DETAILED DESCRIPTION

[0066] In order to make the above-mentioned purposes, features and advantages of the application more obvious and easy to understand, the specific embodiments of the application will be described in detail below with reference to the drawings of the specification.

[0067] In the following description, many specific details are set forth in order to provide a thorough understanding of the application, but the application can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the connotation of the application, therefore the application is not limited by the specific embodiments disclosed below.

[0068] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the application. "In one embodiment" appearing in different places in the specification does not mean the same embodiment, nor is it an independent or alternative embodiment that excludes other embodiments.

[0069] Embodiment 1, refer to Figure 1 and Figure 2For the first embodiment of the present application, the embodiment provides a smart advertisement analysis management method based on blockchain data, including the following steps:

[0070] S1, collecting interaction behavior data generated when a user interacts with advertisement content.

[0071] Further, the interaction behavior data includes interaction operation data, device environment data, interest preference data, behavior sequence data, personalized advertisement data, and target conversion data.

[0072] Specifically, the integrated SDK monitors and collects the user's interaction operation data with the advertisement content in real time, which includes clicking, sliding, long pressing, and other operations. At the same time, device environment data such as device type, operating system, browser version, etc. is also collected. Then, according to the user's operation record, the user's interest preference data is extracted, and the user's interest field is inferred by analyzing the advertisement content and its dwell time, etc. Subsequently, the user's behavior sequence data is generated, which records the user's advertisement interaction behavior at different time points through time series analysis and organizes it into behavior sequence data. Next, the user's interest preference data and behavior sequence data are combined to generate personalized advertisement data, which is used to identify and match suitable advertisement content for the user. Finally, the user's target conversion data is tracked to record whether the user has completed a specific target behavior such as purchase, registration, etc. after interacting with the advertisement, in order to evaluate the actual effect of the advertisement.

[0073] S2, converting the interaction behavior data into advertisement behavior tags in real time, and performing chain association with the previous and subsequent advertisement behavior tags through an encryption hash algorithm and storing them in a blockchain.

[0074] Further, a standardization function is used to normalize the interaction behavior data;

[0075] Wherein, the standardization processing helps to improve the comparability of the data and lays the foundation for the subsequent processing steps.

[0076] The normalized interaction behavior data is mapped to a high-dimensional semantic space through a nonlinear embedding function to generate a corresponding quantum state probability distribution;

[0077] Wherein, the quantum state probability distribution is generated to capture the semantic features in the data.

[0078] Preferably, the nonlinear embedding function is used to capture the complex semantic relationships in the data, making the originally linearly inseparable data linearly separable in high-dimensional space.

[0079] The eigenvalues of the quantum state probability distribution are described using a density matrix and used as semantic features to identify semantic patterns in the interaction behavior data;

[0080] The semantic features include, but are not limited to, semantic feature intensities described by eigenvalues of the quantum state density matrix, and other semantic feature information related to the interaction behavior data.

[0081] It should be noted that the density matrix can not only accurately describe the semantic features in the data, but also reflect the probabilistic properties of the data distribution. By performing clustering analysis and time correlation analysis on the identified semantic patterns, an advertising behavior label corresponding to the interaction behavior data can be generated.

[0082] The identified semantic patterns are subjected to clustering analysis and time correlation analysis to generate an advertising behavior label corresponding to the interaction behavior data.

[0083] Preferably, clustering analysis helps to discover potential patterns and structures in the data, while time correlation analysis reveals the time-dependent relationships in the behavior data.

[0084] The semantic correlation weight between the advertising behavior labels is calculated using the quantum state correlation matrix, and the expression is:

[0085]

[0086] where A ij represents the semantic correlation weight between advertising behavior labels i and j, i and j represent two different advertising behavior labels, represents the complex conjugate quantum state function of advertising behavior label i at time t, ψ j (t) represents the quantum state function of advertising behavior label j at time t, is a Gaussian time weight function, t0 represents the reference time point of the current behavior event, α represents the time weight factor, and dt represents the small time increment in the integration operation.

[0087] It should be noted that ψ j (t) represents the quantum state function of advertising behavior label j at time t, which is derived from the concept of quantum mechanics and is mainly used to capture the dynamic semantic features of the advertising behavior label. Specifically, the quantum state function describes the state of advertising behavior label j at time t, which can be regarded as a probability distribution in a high-dimensional semantic space. The "quantum state function" here is not a real quantum state in physics, but a mathematical model used to represent and analyze complex semantic relationships in advertising behavior data.

[0088] Specifically, the quantum state function can be regarded as a probability wave function, which provides state information of advertising behavior label j at time t. Through this representation method, the changes of advertising behavior labels at different time points can be accurately modeled and analyzed.

[0089] More preferably, the quantum state function is used to describe the advertising behavior tags, which can not only capture the complex semantic relationship in the interaction behavior data, but also accurately model and analyze these relationships through mathematical models, thereby optimizing the advertising placement strategy and improving the advertising effect.

[0090] The semantic correlation weight of all advertising behavior tag pairs (i, j) is combined to form a two-dimensional matrix, forming a semantic correlation matrix;

[0091] It should be noted that the process of using the quantum state correlation matrix to calculate the semantic correlation weight between advertising behavior tags can construct a two-dimensional semantic correlation matrix between advertising behavior tags, and the chain structure can be constructed by the maximum weight path of the semantic correlation matrix to generate the optimal advertising behavior tag chain, thereby optimizing the advertising placement strategy.

[0092] Based on the semantic correlation matrix, all possible advertising behavior tag pair path sets are constructed

[0093] Each advertising behavior tag path is composed of an advertising behavior tag pair, and the weight is represented by the semantic correlation weight between the advertising behavior tag pair.

[0094] Specifically, based on the semantic correlation matrix, all advertising behavior tag pairs are first traversed, and a potential advertising behavior tag path is generated for each advertising behavior tag pair. Each advertising behavior tag path is composed of two tags i and j, and the weight of the advertising behavior tag path is the semantic correlation weight A ij between tags i and j. Then, the combination of all advertising behavior tag pairs is used to construct the advertising behavior tag pair path set

[0095] According to the maximum weight path of the semantic correlation matrix, the chain structure is constructed to generate the optimal advertising behavior tag chain, and the expression is:

[0096]

[0097] wherein, represents the optimal advertising behavior tag chain, represents finding the maximum weight path from all possible advertising behavior tag pair path sets , represents the sum of the semantic correlation weights of all advertising behavior tag pairs (i, j) in the path set;

[0098] Preferably, by calculating the semantic correlation weight between the advertising behavior tags, the most semantically correlated tag path is found, ensuring the accuracy and relevance of advertising, thereby maximizing advertising effectiveness. By constructing the optimal advertising behavior tag chain, advertising placement strategies can be dynamically optimized, improving user conversion rates and the effectiveness of advertising placement, ensuring that advertising content is always highly matched with user needs, achieving personalized recommendations and precision marketing, effectively improving the ROI (return on investment) of advertising placement, and enhancing user experience.

[0099] Based on the optimal advertising behavior tag chain , the encrypted hash value of the optimal advertising behavior tag chain is generated, and the expression is:

[0100]

[0101] where H k represents the encrypted hash value of the kth optimal advertising behavior tag chain, k represents the index variable of the optimal advertising behavior tag chain, SHA3 is a secure hash algorithm, and p k (t) represents the quantum state density function of the kth advertising behavior tag chain at time t, is a Gaussian decay factor, and β represents a time weight parameter.

[0102] It should be noted that by generating the encrypted hash value of the optimal advertising behavior tag chain, the security and tamper resistance of the advertising behavior tag chain are ensured. For newly added advertising behavior tags, the semantic correlation weight with all tags in the existing tag chain needs to be recalculated, the optimal path is updated, and a new encrypted hash value is generated to ensure dynamic optimization of the tag chain.

[0103] When a new advertising behavior tag is added to the advertising behavior tag chain, the semantic correlation weight between the new advertising behavior tag and all advertising behavior tags in the optimal advertising behavior tag chain is recalculated, the optimal path is updated, and the encrypted hash value of the new optimal advertising behavior tag chain is calculated.

[0104] where the newly added advertising behavior tag refers to new behavior tags generated during the advertising placement process. These tags are created based on the latest advertising interaction behavior data of users. They reflect the behavior characteristics of users in the latest advertising interaction, including clicks, swipes, views, conversions, etc. The introduction of these new tags can provide more accurate user behavior analysis, thereby optimizing advertising placement strategies and improving advertising effectiveness. Whenever new interaction behavior data is generated, corresponding new advertising behavior tags are generated, which need to be analyzed for semantic correlation with existing tags to ensure dynamic optimization and updating of the advertising behavior tag chain.

[0105] It should be noted that when the newly added advertising behavior tag is added to the advertising behavior tag chain, the semantic association weight of the newly added advertising behavior tag with all the tags in the existing tag chain needs to be recalculated. This is because the newly added advertising behavior tag may change the original semantic association structure and affect the maximum weight path of the advertising behavior tag chain. The specific steps are as follows: first, calculate the semantic association weight between the new advertising behavior tag and each advertising behavior tag in the maximum weight path. Then, based on these new weights, update the maximum weight path of the advertising behavior tag chain to ensure that the new path reflects the latest association relationship. Finally, perform cryptographic hash processing on the updated maximum weight path to generate a new cryptographic hash value, ensuring the security and tamper resistance of the data.

[0106] The semantic association weight of the newly added advertising behavior tag and the cryptographic hash value of the updated optimal advertising behavior tag chain are stored as new tag information in the blockchain, and each advertising behavior tag chain is stored as a block.

[0107] Preferably, storing each advertising behavior tag chain as a block can ensure the integrity, transparency and tamper resistance of the advertising behavior data, thereby improving the security and credibility of the data.

[0108] A semantic index of each advertising behavior tag chain is established, and a quantum Bloom filter is used to optimize the query efficiency of the advertising behavior tag chain, with the expression being:

[0109]

[0110] where Q(x) represents the result of the quantum Bloom filter, m represents the number of hash functions in the Bloom filter, z represents the index of the hash function in the Bloom filter, b z represents the Boolean value of the zth hash function, γ z represents the weight parameter of the zth dimension, x represents the input query value, represents the symbol conversion term, represents the weight decay function;

[0111] It should be noted that by introducing multi-dimensional weight parameters, the accuracy and efficiency of the query are significantly improved. When the advertising behavior tag chain is updated, the corresponding blockchain and semantic index of the advertising behavior tag chain are updated synchronously to ensure real-time and consistency.

[0112] When the advertising behavior tag chain is updated, the corresponding blockchain and semantic index of the advertising behavior tag chain are updated synchronously to ensure the consistency and integrity of all related data, thereby improving the query efficiency and accuracy of data management.

[0113] S3, data preprocessing is performed on the advertising behavior tag chain, advertising delivery indicators are extracted, a behavior sequence analysis model is used to perform real-time behavior prediction on the advertising delivery indicators, and a dynamically updated user conversion path is output.

[0114] Further, the advertising behavior tag chain is cleaned and standardized, the time series, click rate and conversion rate of user interaction behavior are extracted, and a behavior feature matrix containing advertising delivery indicators is generated based on semantic association weights;

[0115] The semantic association weight is the semantic association weight between the advertising behavior tags calculated by the quantum state association matrix. The semantic association weight reflects the semantic association degree between different advertising behavior tags, which helps to build the advertising behavior tag chain.

[0116] The advertising delivery indicators in the behavior feature matrix are organized into a sliding window sequence in chronological order, and the time interval features between the advertising delivery indicators are calculated to form a behavior sequence containing short-term and long-term dependencies;

[0117] Specifically, the time period is divided into continuous and overlapping windows, each window contains a group of advertising delivery indicators arranged in chronological order, and then the time interval features between the advertising delivery indicators in these windows are calculated to ensure that the data can reflect short-term and long-term behavior dependencies. By this method, not only the local behavior sequence containing short-term dependencies is obtained, but also the long-term dependency features across time periods are captured to form a comprehensive behavior sequence for further analysis and prediction.

[0118] The behavior sequence is input into the behavior sequence analysis model based on LSTM, combining the historical behavior feature matrix and the current behavior feature matrix, to predict the next advertising behavior tag of the user and its conversion probability;

[0119] According to the conversion probability, the advertising behavior tag is filtered and inserted into the current short-term behavior sequence, and the conversion probability is recorded, and a dynamically updated user conversion path is output.

[0120] The user conversion path refers to the user behavior path generated based on the predicted user advertising behavior tag and its conversion probability. The user conversion path reflects the behavior trajectory of the user from seeing the advertisement to completing the conversion process.

[0121] S4, based on the dynamically updated user conversion path, a generative adversarial network is called to generate personalized advertising content based on the user's historical interaction behavior data, record the version and distribution of the personalized advertising content through the advertising behavior tag chain, and push the personalized advertising content to the user.

[0122] Further, based on the user conversion path, the behavior feature matrix and the advertising context are extracted, and a joint feature matrix is generated in combination;

[0123] Specifically, the user behavior feature matrix is extracted, including user interaction behavior data with the advertisement. Then, the advertisement context information is obtained, such as the attributes of the advertisement content, the display position, and the target audience, etc. Then, these user behavior features and the advertisement context information are combined, and a joint feature matrix is generated through weighted processing. This joint feature matrix contains multi-dimensional features of user historical behavior and advertisement content, providing a data basis for further personalized advertisement generation and pushing. In this way, user behavior and advertisement content information can be effectively integrated to achieve more accurate and personalized advertisement placement strategies.

[0124] Based on the semantic association weight between the advertisement behavior tags, the joint feature matrix is weighted processed to generate a high-dimensional feature vector;

[0125] The high-dimensional feature vector is input into the bidirectional generative adversarial network, and the generator generates personalized advertisement content (including advertisement text, images, and videos), and the discriminator verifies the authenticity of the personalized advertisement content and the matching degree with the interaction behavior data;

[0126] Through behavior path analysis (combining user behavior sequence, conversion probability, and other elements), it is verified whether the personalized advertisement content matches the user conversion path, and the relevance and logic of the content are optimized.

[0127] Specifically, the advertisement interaction data of each user at different time points is extracted from the behavior feature matrix, sorted according to the timestamp, and a sequence is created by using a fixed-length window sliding step by step, ensuring that the data in each window represents a continuous time period.

[0128] In the process of constructing each sliding window, the exact time difference between adjacent advertisement placement indicators is calculated as a time interval feature and saved together with the original data in the window. In this way, not only the user's activity pattern in each time period is preserved, but also the timing relationship between activities is captured. By adjusting the size and step of the sliding window, short-term trends in user behavior (such as the last few interactions) and long-term behavior patterns (such as trends over weeks or months) can be effectively identified, forming a comprehensive behavior sequence that reflects both immediate reactions and historical preferences.

[0129] Furthermore, based on the generated personalized advertisement content, semantic features described by quantum state density matrix eigenvalues are extracted, and a unique version identifier is generated using an encryption hash algorithm, and is stored in association with the advertisement behavior tag chain;

[0130] A distribution record is generated for each advertisement content, and the distribution record is stored as a block in the blockchain to generate an advertisement distribution record chain;

[0131] Specifically, detailed information of the captured advertisement is obtained, including but not limited to advertisement ID, target audience characteristics, distribution timestamp, and expected coverage, and these metadata are associated with the identifier of the advertisement content itself; then, a data structure containing all the above information is created as a distribution record of the advertisement content, and a cryptographic hash value of the record is calculated to ensure its integrity and non-tamperability, and then the distribution record is packaged into a block format together with its hash value, ready to be stored in the blockchain; finally, after verifying that the new block meets the requirements of the blockchain protocol, it is linked to the end of the existing blockchain, so that the newly added distribution record becomes part of the advertisement distribution record chain, thus completing the process from generating the distribution record to forming a continuous and tamper-proof advertisement distribution record chain.

[0132] The advertisement content version with the highest conversion probability is dynamically matched by combining the user's advertisement behavior tag chain and the advertisement distribution record chain.

[0133] Specifically, by analyzing the user's historical advertisement behavior tag chain, specific interactive operation data, device environment data, interest preference data, behavior sequence data, personalized advertisement data, and target conversion data are extracted; then, these specific data features are compared with the advertisement content versions in the existing advertisement distribution record chain and their distribution effects to evaluate the conversion probability of different versions of advertisements for users with similar interaction patterns; then, machine learning algorithms are used to calculate the potential response of the current user to each advertisement version in real time, and to predict which version is most likely to promote the user to complete the expected conversion behavior; finally, the advertisement content version with the highest conversion probability is selected to ensure that it is the best option that meets the user's current behavior path and personal preferences, thus achieving precise pushing.

[0134] The selected advertisement content version is pushed to the user through a content distribution interface.

[0135] S5, after the user receives the personalized advertisement content, the user's personalized interaction behavior data with the personalized advertisement content is recorded in real time and stored in the advertisement behavior tag chain, and the advertisement behavior tag chain updates the advertisement delivery indicators according to the real-time recording of the personalized interaction behavior data.

[0136] The SDK (Software Development Kit) integrated by the local application monitors click, view, and conversion data, and collects personalized interaction behavior data in a time-stamped manner;

[0137] The SDK is used to monitor user interaction with the advertisement, such as clicking, viewing, etc., and record conversion data.

[0138] More preferably, through the SDK integrated by the local application, the user's every interaction with the advertisement can be accurately captured. This not only includes direct operations (such as clicks), but also indirect reactions (such as dwell time). Marking these data with timestamps can ensure the accuracy and reliability of subsequent analysis.

[0139] The personalized interaction behavior data is encrypted and hashed, the advertisement behavior label is updated, and after being semantically associated with the historical advertisement behavior label chain, it is stored in the blockchain;

[0140] It should be noted that the collected data is encrypted and hashed, which on the one hand guarantees the security of user data, and on the other hand simplifies the data structure for efficient storage. The updated advertisement behavior label reflects the latest changes in user interest, and when it is semantically associated with the historical label chain, it forms a continuous and evolving user behavior trajectory. This process enhances the memory capacity of the system and helps to better understand user needs.

[0141] The click, view, and conversion data are extracted from the updated advertisement behavior label chain and fused with the behavior feature matrix to dynamically correct the real-time values of the advertisement delivery indicators.

[0142] It should be noted that by fusing the latest user interaction data (such as clicks, views, and conversions) with the historical behavior feature matrix, subtle changes in user behavior patterns can be captured. This real-time data integration ensures that the advertisement delivery strategy is always based on the latest and most accurate information, thereby improving the relevance and effectiveness of the advertisement content.

[0143] More preferably, by fusing the latest user interaction data with the historical behavior feature matrix in real time, this process can capture subtle changes in user behavior patterns, which can respond to changes in market trends and shifts in consumer preferences in real time, ensuring that the advertisement reaches the target audience at the most appropriate time, thereby maximizing the return on investment of the advertisement.

[0144] The embodiment also provides an intelligent advertisement analysis management system based on blockchain data, comprising a data acquisition module, a storage module, a behavior prediction module, a pushing module and an interaction record module; the data acquisition module is used for acquiring interaction behavior data generated when a user interacts with advertisement content; the storage module is used for converting the interaction behavior data into an advertisement behavior tag in real time, performing chain connection with previous and subsequent advertisement behavior tags through an encryption hash algorithm and storing in a blockchain; the behavior prediction module is used for performing data preprocessing on the advertisement behavior tag chain, extracting an advertisement launching index, performing real-time behavior prediction on the advertisement launching index through a behavior sequence analysis model and outputting a dynamically updated user conversion path; the pushing module is used for calling a generative adversarial network based on the dynamically updated user conversion path, generating personalized advertisement content according to historical interaction behavior data of the user, recording a version and distribution of the personalized advertisement content through the advertisement behavior tag chain and pushing the personalized advertisement content to the user; the interaction record module is used for recording personalized interaction behavior data of the user and the personalized advertisement content in real time after the user receives the personalized advertisement content and storing in the advertisement behavior tag chain, and the advertisement behavior tag chain updates the advertisement launching index according to the real-time recorded personalized interaction behavior data.

[0145] The embodiment also provides a computer device suitable for the intelligent advertisement analysis management method based on blockchain data, comprising a memory and a processor; the memory is used for storing computer executable instructions, and the processor is used for executing the computer executable instructions to realize the intelligent advertisement analysis management method based on blockchain data proposed in the above embodiment.

[0146] The computer device can be a terminal, and the computer device comprises a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. The processor of the computer device is used for providing computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used for wired or wireless communication with external terminals. The wireless communication can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0147] The embodiment also provides a storage medium on which a computer program is stored, the program being executed by a processor to implement the intelligent advertisement analysis management method based on blockchain data proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk, or an optical disk.

[0148] To sum up, by introducing the blockchain technology, the advertisement data has the tamper-proof and high security in the transmission and storage process, which greatly improves the security and privacy protection of the data. Through real-time conversion and chain storage of the user interaction behavior data, a dynamically updated advertisement behavior label chain is generated, so that the interest preferences of the user can be more accurately captured. By using the generative adversarial network technology, personalized advertisement content is generated according to the historical behavior data of the user, which not only improves the relevance and attractiveness of the advertisement, but also records the personalized interaction behavior data of the user in real time after the user receives the advertisement content, further optimizes the advertisement delivery index and the user conversion path. In summary, the present application has significant beneficial effects in terms of data security, personalized advertisement generation, and real-time behavior prediction, and can effectively improve the accuracy and effect of advertisement delivery.

[0149] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application, and all of them should be covered in the scope of the claims of the present application.

Claims

1. A method for intelligent advertisement analysis management based on blockchain data, characterized in that: The application relates to a method for constructing an advertisement behavior label chain based on quantum computing. Collecting interaction behavior data generated when a user interacts with advertisement content; Real-time conversion of the interaction behavior data into advertisement behavior labels, chain connection with previous and subsequent advertisement behavior labels through an encryption hash algorithm, and storage in a block chain, the specific steps being as follows, Standardization function is used for normalizing the interaction behavior data; The normalized interaction behavior data is mapped to a high-dimensional semantic space through a nonlinear embedding function to generate corresponding quantum state probability distribution; Density matrix is used for describing eigenvalues of the quantum state probability distribution and taking the eigenvalues as semantic features to identify semantic patterns in the interaction behavior data; Cluster analysis and time correlation analysis are performed on the identified semantic patterns to generate advertisement behavior labels corresponding to the interaction behavior data; A quantum state correlation matrix is used for calculating semantic correlation weights between the advertisement behavior labels; A two-dimensional matrix formed by the semantic correlation weights of all advertisement behavior label pairs (i, j) is used to form a semantic correlation matrix; Based on the semantic association matrix, all possible advertising behavior label pair path sets are constructed A chain structure is constructed according to the maximum weight path of the semantic correlation matrix to generate an optimal advertisement behavior label chain; On the basis of the optimal advertising behavior tag chain An encrypted hash value of the optimal advertising behavior tag chain is generated. When a new advertisement behavior label is added to the advertisement behavior label chain, the semantic correlation weights of the new advertisement behavior label and all advertisement behavior labels in the optimal advertisement behavior label chain are recalculated, the optimal path is updated, and the encryption hash value of the new optimal advertisement behavior label chain is calculated; The semantic correlation weights of the new advertisement behavior label and the updated encryption hash value of the optimal advertisement behavior label chain are stored in the block chain as new label information, and each advertisement behavior label chain is taken as a block; A semantic index of each advertisement behavior label chain is established, and a quantum Bloom filter is used to optimize the query efficiency of the advertisement behavior label chain; When the advertisement behavior label chain is updated, the corresponding block chain and the semantic index of the advertisement behavior label chain are synchronously updated; Data preprocessing is performed on the advertisement behavior label chain, advertisement delivery indexes are extracted, a behavior sequence analysis model is used for real-time behavior prediction of the advertisement delivery indexes, and a dynamically updated user conversion path is output; Based on the dynamically updated user conversion path, a generative adversarial network is called, personalized advertisement content is generated according to historical interaction behavior data of the user, the version and distribution of the personalized advertisement content are recorded through the advertisement behavior label chain, and the personalized advertisement content is pushed to the user; After the user receives the personalized advertisement content, personalized interaction behavior data of the user and the personalized advertisement content are recorded in real time and stored in the advertisement behavior label chain, and the advertisement behavior label chain updates the advertisement delivery indexes according to the real-time recorded personalized interaction behavior data. 2.The blockchain data-based intelligent advertisement analysis management method of claim 1, wherein: The interaction behavior data includes interaction operation data, device environment data, interest preference data, behavior sequence data, personalized advertisement data and target conversion data. 3.The blockchain data-based intelligent advertisement analysis management method of claim 2, wherein: The quantum state correlation matrix is used for calculating the semantic correlation weights between the advertisement behavior labels, and the expression is as follows: where A ij denotes the semantic association weight between the advertising behavior labels i and j, i and j denote two different advertising behavior labels, denotes the complex conjugate quantum state function of the advertising behavior label i at time t, ψ j (t) denotes the quantum state function of the advertising behavior label j at time t, is a Gaussian time weight function, t0denotes the reference time point of the current behavior event, a denotes the time weight factor, and dt denotes the small time increment in the integration operation; The chain structure is constructed according to the maximum weight path of the semantic correlation matrix to generate the optimal advertisement behavior label chain, and the expression is as follows: wherein, represents the optimal ad behavior tag chain, represents finding the maximum weight path from all possible ad behavior tag pair paths set, represents summing the semantic association weights for all ad behavior tag pairs (i,j) in the path set; The optimal advertising behavior tag chain On the basis of the optimal advertising behavior tag chain, the encryption hash value of the optimal advertising behavior tag chain is generated, and the expression is: where H k denotes the encrypted hash value of the kth optimal advertising behavior label chain, k denotes the index variable of the optimal advertising behavior label chain, SHA3 is a secure hash algorithm, and ρ k (t) denotes the quantum state density function of the kth advertising behavior label chain at time t, denotes a Gaussian decay factor, and β denotes a time weight parameter; The semantic index of each advertisement behavior label chain is established, and the quantum Bloom filter is used to optimize the query efficiency of the advertisement behavior label chain, and the expression is as follows: where Q(x) represents the result of the quantum Bloom filter, m represents the number of hash functions in the Bloom filter, z represents the index of the hash function in the Bloom filter, b z represents the Boolean value of the zth hash function, γ z represents the weight parameter of the zth dimension, x represents the input query value, represents the symbol conversion term, represents the weight decay function. 4.The blockchain data-based intelligent advertisement analysis management method of claim 3, wherein: The data preprocessing of the advertisement behavior label chain, the extraction of the advertisement delivery index, the real-time behavior prediction of the advertisement delivery index by using the behavior sequence analysis model, and the output of the dynamically updated user conversion path are as follows, The advertisement behavior label chain is cleaned and standardized, the time sequence, click rate and conversion rate of user interaction behavior are extracted, and the behavior feature matrix containing the advertisement delivery index is generated based on the semantic association weight; The advertisement delivery indexes in the behavior feature matrix are organized into a sliding window sequence in time sequence, and the time interval features between the advertisement delivery indexes are calculated to form a behavior sequence containing short-term and long-term dependencies; The behavior sequence is input into the behavior sequence analysis model based on LSTM, the historical behavior feature matrix and the current behavior feature matrix are combined, and the next advertisement behavior label and its conversion probability of the user are predicted; According to the conversion probability, the advertisement behavior label is filtered and inserted into the current short-term behavior sequence, and the conversion probability is recorded, and the dynamically updated user conversion path is output. 5.The blockchain data-based intelligent advertisement analysis management method of claim 4, wherein: Based on the dynamically updated user conversion path, a generative adversarial network is called to generate personalized advertisement content according to the user's historical interaction behavior data, and the specific steps are as follows, Based on the user conversion path, the behavior feature matrix and the advertisement context are extracted, and the joint feature matrix is combined; Based on the semantic association weight between the advertisement behavior labels, the joint feature matrix is weighted to generate a high-dimensional feature vector; The high-dimensional feature vector is input into the bidirectional generative adversarial network, the generator generates personalized advertisement content, and the discriminator verifies the authenticity of the personalized advertisement content and the matching degree with the interaction behavior data; Through behavior path analysis, it is verified whether the personalized advertisement content matches the user conversion path, and the relevance and logic of the content are optimized. 6.The blockchain data-based intelligent advertisement analysis management method of claim 5, wherein: The version and distribution of the personalized advertisement content are recorded through the advertisement behavior label chain, and the personalized advertisement content is pushed to the user, and the specific steps are as follows, Based on the generated personalized advertisement content, the semantic features described by the eigenvalues of the quantum state density matrix are extracted, the unique version identifier is generated by using the encryption hash algorithm, and is stored in association with the advertisement behavior label chain; A distribution record is generated for each advertisement content, the distribution record is stored as a block in the blockchain, and an advertisement distribution record chain is generated; The advertisement content version with the highest conversion probability is dynamically matched based on the user's advertisement behavior label chain and the advertisement distribution record chain; The selected advertisement content version is pushed to the user through the content distribution interface. 7.The blockchain data-based intelligent advertisement analysis management method of claim 6, wherein: After the user receives the personalized advertisement content, the personalized interaction behavior data of the user and the personalized advertisement content is recorded in real time and stored in the advertisement behavior label chain, and the advertisement behavior label chain updates the advertisement delivery index according to the real-time recorded personalized interaction behavior data, and the specific steps are as follows, The SDK integrated by the local application monitors the click, view and conversion data, and collects the personalized interaction behavior data in the form of timestamp; The personalized interaction behavior data is encrypted and hashed, the advertisement behavior label is updated, and it is stored in the blockchain after being semantically associated with the historical advertisement behavior label chain; Click, view and conversion data are extracted from the updated advertising behavior tag chain and fused with the behavior feature matrix to dynamically correct the real-time values of the advertising delivery indicators.

8. An intelligent advertisement analysis management system based on blockchain data, based on the intelligent advertisement analysis management method based on blockchain data according to any one of claims 1 to 7, characterized in that: The method comprises a data collection module, a storage module, a behavior prediction module, a pushing module and an interaction record module. The data collection module is configured to collect interaction behavior data generated when a user interacts with advertising content. The storage module is configured to convert the interaction behavior data into advertising behavior tags in real time, chain-link the advertising behavior tags with previous and subsequent advertising behavior tags through an encryption hash algorithm and store the advertising behavior tags in a blockchain. The behavior prediction module is configured to perform data preprocessing on the advertising behavior tag chain, extract advertising delivery indicators, perform real-time behavior prediction on the advertising delivery indicators using a behavior sequence analysis model and output a dynamically updated user conversion path. The pushing module is configured to call a generative adversarial network based on the dynamically updated user conversion path, generate personalized advertising content according to historical interaction behavior data of a user, record versions and distribution of the personalized advertising content through the advertising behavior tag chain and push the personalized advertising content to the user. The interaction record module is configured to record personalized interaction behavior data of a user and personalized advertising content in real time after the user receives the personalized advertising content and store the personalized interaction behavior data in the advertising behavior tag chain, and the advertising behavior tag chain updates advertising delivery indicators according to the real-time recorded personalized interaction behavior data. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is characterized in that: The processor executes the computer program to implement the steps of the intelligent advertising analysis and management method based on blockchain data according to any one of claims 1-7.

10. A computer readable storage medium having stored thereon a computer program, characterized in that: The computer program is executed by the processor to implement the steps of the intelligent advertising analysis and management method based on blockchain data according to any one of claims 1-7.

Images