Multi-platform advertising effect analysis method and system based on artificial intelligence

Abstract

The present invention relates to the field of computer technology, and provides a multi-platform advertising delivery effect analysis method and system based on artificial intelligence. The method includes: constructing an advertising delivery structure tree and an advertising delivery knowledge graph; starting from the root node of the advertising delivery structure tree, combining the semantic information of each node mapped in the advertising delivery knowledge graph by the association mapping relationship, traversing the advertising delivery data along different paths, analyzing the association relationship and data change trend between nodes at each level, and obtaining hierarchical effect information; based on the relationship between entities in the advertising delivery knowledge graph, combining the hierarchy of each entity mapped in the advertising delivery structure tree by the association mapping relationship, inferring the delivery effect, and obtaining potential effect information; performing delivery effect decision analysis based on the hierarchical effect information and the potential effect information, and obtaining delivery optimization information for multi-platform advertising delivery. The embodiment of the present invention improves the timeliness and effectiveness of the adjustment of advertising delivery strategies.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an artificial intelligence-based multi-platform advertising effect analysis method and system. Background Art

[0002] In the advertising sector, one existing method for analyzing advertising effectiveness is based on a rules engine. This method pre-defines a series of rules, such as fixed criteria like the time of ad placement, platform, and target audience, to match and analyze ad data and determine whether the advertising has met performance targets. For example, if an ad reaches a set threshold of impressions on a specific platform within a specific time period for a specific age group, the ad is considered to have achieved good results in this regard.

[0003] However, once established, rule-based advertising effectiveness analysis methods are relatively fixed, making them difficult to adapt to the complex and ever-changing advertising environment and diverse advertising needs. With the increasing number of advertising platforms and the increasing complexity of audience behavior, new factors influencing advertising effectiveness continue to emerge. Fixed rules cannot promptly incorporate these new factors, resulting in an inability to accurately and comprehensively analyze advertising effectiveness, making it difficult to identify potential optimization opportunities, and reducing the timeliness and effectiveness of advertising strategy adjustments. Summary of the Invention

[0004] The present invention provides an artificial intelligence-based multi-platform advertising delivery effect analysis method and system, which are used to improve the timeliness and effectiveness of advertising delivery strategy adjustments.

[0005] In a first aspect, the present invention provides a multi-platform advertising effectiveness analysis method based on artificial intelligence, comprising:

[0006] Constructing an advertising placement structure tree and an advertising placement knowledge graph; the advertising placement structure tree is constructed by taking a preset advertising campaign as a root node, different advertising placement platforms as child nodes under the root node, and advertising placement elements of different advertising placement platforms as different hierarchical nodes of its child nodes; the advertising placement knowledge graph is constructed by taking different advertising placement platforms and advertising placement subjects of different advertising placement platforms as entities, and taking relationships between entities as edges;

[0007] Starting from the root node of the advertising placement structure tree, combined with the semantic information of each node mapped to the advertising placement knowledge graph by the association mapping relationship, the advertising placement data is traversed along different paths, and the association relationships and data change trends between the nodes at each level are analyzed to obtain hierarchical effect information of advertising placement; the association mapping relationship represents the mapping relationship between the entities in the advertising placement knowledge graph and the nodes in the advertising placement structure tree;

[0008] Based on the relationship between entities in the advertising knowledge graph, combining the association mapping relationship with the hierarchy of each entity mapped in the advertising structure tree, the advertising effect is inferred to obtain potential effect information of the advertising;

[0009] Based on the hierarchical effect information and the potential effect information, a delivery effect decision analysis is performed to obtain delivery optimization information for multi-platform advertising.

[0010] In a second aspect, the present invention further provides an artificial intelligence-based multi-platform advertising delivery effect analysis system, which is applied to the artificial intelligence-based multi-platform advertising delivery effect analysis method as described in the first aspect; the artificial intelligence-based multi-platform advertising delivery effect analysis system includes:

[0011] A construction module is used to construct an advertising placement structure tree and an advertising placement knowledge graph; the advertising placement structure tree is constructed by taking a preset advertising campaign as a root node, different advertising placement platforms as child nodes under the root node, and advertising placement elements of different advertising placement platforms as different hierarchical nodes of its child nodes; the advertising placement knowledge graph is constructed by taking different advertising placement platforms and advertising placement subjects of different advertising placement platforms as entities, and taking the relationships between entities as edges;

[0012] An effect trend analysis module is configured to start from the root node of the advertising placement structure tree, combine the semantic information of each node mapped to the advertising placement knowledge graph by the association mapping relationship, traverse the advertising placement data along different paths, analyze the association relationships and data change trends between nodes at each level, and obtain hierarchical effect information of advertising placement; the association mapping relationship represents the mapping relationship between the entities in the advertising placement knowledge graph and the nodes in the advertising placement structure tree;

[0013] An effect inference module is used to perform advertising effect inference based on the relationship between entities in the advertising knowledge graph and the hierarchy of entities mapped to the advertising structure tree by combining the association mapping relationship to obtain potential effect information of the advertising;

[0014] The effect decision analysis module is used to perform delivery effect decision analysis based on the hierarchical effect information and the potential effect information to obtain delivery optimization information for multi-platform advertising delivery.

[0015] In a third aspect, the present invention also provides an electronic device comprising: a memory for storing a computer software program; and a processor for reading and executing the computer software program, thereby implementing any of the above-mentioned artificial intelligence-based multi-platform advertising delivery effect analysis methods.

[0016] In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium, wherein the storage medium stores a computer software program, and when the computer software program is executed by a processor, it implements any of the above-mentioned artificial intelligence-based multi-platform advertising delivery effect analysis methods.

[0017] In a fifth aspect, the present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned artificial intelligence-based multi-platform advertising delivery effect analysis methods.

[0018] The artificial intelligence-based multi-platform advertising effect analysis method provided by the embodiment of the present invention can clearly present the hierarchical architecture of multi-platform advertising by constructing a multi-platform advertising structure tree, intuitively display the inherent correlation and data change trends of advertising on each platform, and make the analysis no longer limited to simple matching under fixed rules. Generating an advertising knowledge graph and performing semantic reasoning can mine the potential complex relationships and semantic information between entities in advertising, making up for the defect that fixed rules cannot incorporate new factors. Therefore, the association mapping between the structure tree and the knowledge graph and the subsequent comprehensive analysis can comprehensively and deeply analyze the advertising effect from both hierarchical and semantic dimensions, and promptly discover new factors and potential optimization space that affect the advertising effect, thereby generating more accurate and effective optimization suggestions, adapting to the complex and changing advertising environment, and improving the timeliness and effectiveness of advertising strategy adjustments. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a flowchart of a multi-platform advertising delivery effect analysis method based on artificial intelligence provided by an embodiment of the present invention;

[0020] Figure 2 This is a schematic diagram of the structure of a multi-platform advertising delivery effect analysis system based on artificial intelligence provided by an embodiment of the present invention;

[0021] Figure 3 An embodiment diagram of an electronic device provided by an embodiment of the present invention;

[0022] Figure 4 An embodiment diagram of a computer-readable storage medium provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0024] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the specified features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0025] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or illustration". Any embodiment of the present invention described as "for example" is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed herein.

[0026] Optional, see Figure 1 , Figure 1 : This is a flow chart of the AI-based multi-platform advertising delivery effect analysis method provided by the present invention. In the embodiment of the present invention, the AI-based multi-platform advertising delivery effect analysis method is executed by an advertising analysis system. Therefore, the AI-based multi-platform advertising delivery effect analysis method includes:

[0027] Step 10: Construct an advertising structure and knowledge graph. The structure is constructed by taking the pre-set advertising campaign as the root node, the different advertising platforms as sub-nodes, and the advertising elements of different advertising platforms as sub-nodes. The knowledge graph is constructed by taking the different advertising platforms and their advertising entities as entities, and the relationships between entities as edges.

[0028] Optionally, the advertising structure tree is constructed with a pre-set advertising campaign as the root node, where the root node represents the core of the entire advertising project. Furthermore, the advertising analysis system treats different advertising platforms, such as Xyin Platform, Xxin Platform, Xdu Platform, and Xshu Platform, as child nodes under the root node. Each advertising platform has its own advertising elements, such as advertising time, budget, and target audience. These elements are then constructed as different levels of nodes under the child nodes, layer by layer, forming a hierarchical tree structure.

[0029] Furthermore, the construction of the advertising knowledge graph takes different advertising platforms and the advertising entities on these platforms (such as advertisers, agents, user groups, etc.) as entities. There are various relationships between the entities. For example, when an advertiser places advertisements on the Xyin platform, "advertiser" and "Xyin platform" are two entities, and "placing advertisements on the Xyin platform" is the relationship between them. These relationships are used as edges to connect the various entities and construct a knowledge graph.

[0030] In one embodiment, for example, an online education course advertising campaign is underway. First, "Online Education Course Advertising Campaign" is used as the root node of the advertising structure tree. Next, "Xinyin Platform," "Xinxin Platform," and "Xdu Platform" are added as child nodes under the root node. Under the "Xinyin Platform" child node, further advertising elements such as "Delivery Time," "Delivery Budget," and "Target Audience (Ages 18-35, Interested in Education)" are added as child nodes. Under the "Xinxin Platform" child node, elements such as "Delivery Time," "Copy Content," and "Target Audience (Bachelor's Degree or Above, Followers of Education-Related Public Accounts)" are added. Under the "Xdu Platform" child node, elements such as "Keyword Settings," "Bidding Strategy," and "Search Audience (People Who Have Searched for Education-Related Keywords)" are added to complete the construction of the advertising structure tree. When constructing the advertising knowledge graph, "Xinyin Platform," "Xinxin Platform," "Xdu Platform," "Online Education Institution (Advertiser)," and "Potential Students (User Group)" are added as entities. Establish relationships between entities, such as the relationship between "online education institutions" and "Xyin platform" is "placing advertisements on the Xyin platform"; the relationship between "potential students" and "Xyin platform" is "browsing advertisements on the Xyin platform"; the relationship between "online education institutions" and "Xdu platform" is "setting keyword advertisements on the Xdu platform", etc., in order to construct a knowledge graph for advertising placement.

[0031] Step 20, starting from the root node of the advertising placement structure, combines the semantic information of each node mapped to the advertising placement knowledge graph by the association mapping relationship, traverses the advertising placement data along different paths, analyzes the association relationships and data change trends between nodes at each level, and obtains hierarchical advertising effect information. The association mapping relationship represents the mapping relationship between entities in the advertising placement knowledge graph and nodes in the advertising placement structure.

[0032] Furthermore, the advertising analysis system performs relationship mapping between the entities in the advertising delivery knowledge graph and the nodes in the advertising delivery structure tree to obtain an association mapping relationship. Therefore, it can be understood that the association mapping relationship represents the mapping relationship between the entities in the advertising delivery knowledge graph and the nodes in the advertising delivery structure tree.

[0033] Furthermore, starting from the root node of the advertising placement structure, the corresponding nodes in the advertising placement knowledge graph are found based on the association mapping relationships, and the semantic information of these nodes is obtained. The advertising placement data is then traversed along different paths in the structure. During this traversal, the associations between nodes at each level are analyzed, such as the impact of changes in the placement budget of a particular advertising platform on ad exposure. Data trends are also observed, such as how the conversion rates of different platforms change over time, to obtain hierarchical information on the advertising placement effect, as described in steps 201 to 204.

[0034] Step 30: Based on the relationship between entities in the advertising knowledge graph, combined with the association mapping relationship, the hierarchy of each entity mapped in the advertising structure tree is used to infer the advertising effect, and the potential effect information of the advertising is obtained.

[0035] Furthermore, the advertising analysis system uses the relationships between entities in the advertising knowledge graph, combined with associated mappings, to locate the corresponding hierarchies for each entity in the advertising structure tree. By analyzing these hierarchical relationships and the relationships between entities, the advertising effectiveness can be inferred. For example, based on the relationships between advertisers and different platforms in the knowledge graph, as well as the relationships between platform user groups, the system can infer the potential effects of increasing advertising targeting a specific user group on a particular platform, thereby obtaining information on the potential effectiveness of advertising, as described in steps 301 to 304.

[0036] Step 40: Perform a delivery effect decision analysis based on the hierarchical effect information and the potential effect information to obtain delivery optimization information for multi-platform advertising delivery.

[0037] Furthermore, the advertising analysis system integrates hierarchical effect information and potential effect information to conduct a comprehensive delivery effect decision analysis. During the analysis process, it considers factors such as the actual performance of different platforms, potential improvement space, and delivery costs, and formulates delivery optimization information for multi-platform advertising, including adjusting the delivery budget allocation of each platform, optimizing the advertising delivery strategy, adjusting the target audience, etc., as described in steps 401 to 404.

[0038] By constructing a multi-platform advertising delivery structure tree, the embodiment of the present invention can clearly present the hierarchical architecture of multi-platform advertising delivery, intuitively display the inherent correlation and data change trends of advertising delivery on each platform, and make the analysis no longer limited to simple matching under fixed rules. Generating an advertising delivery knowledge graph and performing semantic reasoning can dig out the potential complex relationships and semantic information between entities in advertising delivery, making up for the defect that fixed rules cannot incorporate new factors. Therefore, the association mapping between the structure tree and the knowledge graph and the subsequent comprehensive analysis can comprehensively and deeply analyze the advertising delivery effect from the two dimensions of hierarchy and semantics, and promptly discover new factors and potential optimization space that affect the advertising delivery effect, thereby generating more accurate and effective optimization suggestions, adapting to the complex and changing advertising delivery environment, and improving the timeliness and effectiveness of advertising delivery strategy adjustments.

[0039] In one embodiment, steps 201 to 204 are described as follows:

[0040] Step 201, starting from the root node of the advertising placement structure tree, locates the first entity associated with the root node in the advertising placement knowledge graph according to the association mapping relationship, and generates an initial traversal path starting from the root node entity based on the similarity and association between the semantic information of the first entity.

[0041] Optionally, the advertising analysis system starts from the root node "Online Education Course Advertising Campaign" of the advertising placement structure tree and locates the first entity associated with it in the advertising placement knowledge graph based on a pre-set association mapping relationship. The association mapping relationship clarifies the correspondence rules between the structure tree nodes and the knowledge graph entities, and thus finds the entity corresponding to the root node through these rules, such as "Online Education Course Promotion Project". Furthermore, the advertising analysis system analyzes the similarity and association between the semantic information of the first entity and other entities in the knowledge graph. For example, through a semantic analysis algorithm (such as the cosine similarity algorithm), entities with similar semantics or business associations to "Online Education Course Promotion Project" are identified, such as "Online Education Market Promotion" and "Education and Training Advertising Placement". Based on these associations, an initial traversal path starting from the root node entity is generated.

[0042] Continuing with the scenario of "online education course advertising campaigns," the advertising analysis system locates the first entity, "online education course promotion project," in the advertising knowledge graph based on the association mapping relationship. Through semantic analysis, it was found that the semantics of the "online education market promotion" entity are highly similar to those of the "online education course promotion project," both of which revolve around the online education promotion business. At the same time, the "education and training advertising" entity has a business association with the "online education course promotion project," both of which fall within the scope of advertising. Based on these analyses, the advertising analysis system generates an initial traversal path, starting from the "online education course promotion project," and sequentially connecting "online education market promotion" and "education and training advertising."

[0043] In step 202, the child nodes corresponding to different advertising delivery platforms are found in the advertising delivery structure tree along the initial traversal path, the second entity corresponding to the child node is found in the advertising delivery knowledge graph according to the association mapping relationship, and the initial traversal path is expanded based on the semantic information of the second entity to obtain the expanded traversal path.

[0044] Furthermore, along the initial traversal path, the child nodes corresponding to different advertising delivery platforms are found in the advertising delivery structure tree, such as "Xyin Platform", "Xxin Platform", and "Xdu Platform". Furthermore, the advertising analysis system finds the second entities corresponding to these child nodes in the advertising delivery knowledge graph based on the association mapping relationship, such as "Xyin Platform", "Xxin Platform Advertising Platform", and "Xdu Platform". Furthermore, the advertising analysis system mines the association with other entities in the existing path based on the semantic information of the second entity. For example, by analyzing the relationship between the "Xyin Platform" entity and the "Online Education Market Promotion" entity already in the initial traversal path, it is found that the Xyin Platform has an advantage in the dissemination of short videos in the online education market promotion. Based on this, the entity path related to the "Xyin Platform" and having a semantic association is added to the initial traversal path to expand the initial traversal path and obtain a more comprehensive traversal path.

[0045] Continuing with the generated initial traversal path, the advertising analysis system finds the "X Music Platform" child node in the advertising placement structure tree and, based on the associated mapping relationship, locates the second entity, "X Music Platform," in the knowledge graph. Analysis of the semantic information for "X Music Platform" reveals a close connection with "online education market promotion," and that the X Music Platform's short video promotion is a key channel for online education market promotion. Therefore, the advertising analysis system adds "X Music Platform" and its related entity paths, such as "X Music Platform Education Short Video Promotion" and "X Music Platform Education Advertising Audience," to the initial traversal path, thereby obtaining an expanded traversal path.

[0046] In step 203, for the advertising delivery element node of the advertising delivery platform, find the element node related to the current path in the advertising delivery structure tree, and fuse the corresponding element semantic information with the corresponding entity semantic information in the advertising delivery knowledge graph to obtain a fused semantic information vector.

[0047] Furthermore, for the advertising delivery element nodes of the advertising delivery platform, the advertising analysis system finds the element nodes related to the current expanded traversal path in the advertising delivery structure tree. For example, for the "X Music Platform", element nodes such as "delivery time", "delivery budget", and "target audience" are found.

[0048] Furthermore, the advertising analysis system integrates the semantic information corresponding to these feature nodes, such as "Xyin platform advertising hours are from 7:00 PM to 9:00 PM on weekdays," "Xyin platform advertising budget is 800 yuan per day," and "Xyin platform target audience is 18-35 years old," with the semantic information of the corresponding entities in the advertising knowledge graph. Using semantic fusion algorithms (such as word vector concatenation), the semantic information of the feature in the structure tree and the semantic information of the corresponding entities in the knowledge graph are converted into vectors in a unified format. These vectors are then combined to form a fused semantic information vector, providing a more comprehensive semantic information foundation for subsequent data traversal and analysis.

[0049] Continuing in the scenario of "Xyin Platform", find element nodes such as "delivery time", "delivery budget", and "target audience" in the advertising delivery structure tree. The semantic information corresponding to "delivery time" is "7-9 pm on weekdays". The semantic information of the "Xyin Platform Delivery Time" entity in the knowledge graph contains the active period data of Xyin platform users; the semantic information corresponding to "delivery budget" is "800 yuan per day", and the "Xyin Platform Advertising Budget Allocation" entity in the knowledge graph has relevant budget usage information; the semantic information corresponding to "target audience" is "people aged 18-35 years old", and the "Xyin Platform Education Advertising Audience Portrait" entity in the knowledge graph has a detailed description of audience characteristics. The embodiment of the present invention uses a word vector splicing algorithm to convert these semantic information from the structure tree and the knowledge graph into vector form and splice them to obtain a fused semantic information vector, which integrates multi-dimensional semantic information about the advertising delivery elements of the Xyin platform.

[0050] Step 204 , traverse the advertising delivery data based on the expanded traversal path and the fused semantic information vector, analyze the association relationship between nodes at each level and the data change trend, and obtain hierarchical effect information of the advertising delivery.

[0051] Furthermore, the advertising analysis system traverses the advertising data based on the expanded traversal path and the fused semantic information vector, analyzes the correlation between nodes at each level and the data change trend, and obtains hierarchical effect information of advertising, as specifically described in steps 2041 to 2044.

[0052] The embodiments of the present invention can comprehensively sort out advertising delivery data, construct a complete traversal path starting from the root node, integrate multi-dimensional semantic information, accurately analyze the correlation relationship and data change trend between nodes at each level, and obtain clearly layered advertising delivery hierarchical effect information. Therefore, it is possible to deeply understand the specific impact of different advertising delivery platforms and various delivery elements on the advertising delivery effect, and provide strong data support and decision-making basis for subsequent advertising delivery strategy adjustments and resource optimization configuration, so that advertising delivery can be more in line with market demand and user characteristics, thereby adapting to the complex and changeable advertising delivery environment, and improving the timeliness and effectiveness of advertising delivery strategy adjustments.

[0053] In one embodiment, steps 2041 to 2044 are described as follows:

[0054] Step 2041: Determine the semantic information difference weight of each traversal path based on the total difference of the semantic information of each node on each traversal path in the expanded traversal path, and screen each traversal path based on the semantic information difference weight to obtain the target traversal path in the expanded traversal path.

[0055] Optionally, for each expanded traversal path, the advertising analysis system calculates the total variance of the semantic information of each node along each traversal path. By comparing the features of the node semantic information (such as keywords and topic categories), embodiments of the present invention employ a suitable variance calculation method (such as the Jaccard distance algorithm) to quantify the degree of variance. Based on the total variance, a semantic information variance weight is determined for each traversal path. Paths with higher variance receive a greater weight, indicating that the path contains more unique and valuable information.

[0056] Furthermore, the advertising analysis system sets a screening threshold based on the weight of semantic information differences, selects paths with higher weights as target traversal paths, and focuses on key information for subsequent analysis.

[0057] Continuing with the "Online Education Course Advertising Campaign", the expanded traversal path obtained by the advertising analysis system includes multiple paths. For example, Path A: "Online Education Course Promotion Project → Online Education Market Promotion → Xyin Platform → Xyin Platform Educational Short Video Promotion → Xyin Platform Delivery Time"; Path B: "Online Education Course Promotion Project → Education and Training Advertising → Xxin Platform Advertising Platform → Xxin Platform Copywriting Content → Xxin Platform Targeted Audience". The system calculates the total difference in semantic information of each node in Path A, and compares the node keywords and topic categories using the Jaccard distance algorithm. It is found that the difference in semantic information of its nodes is relatively high, and a higher semantic information difference weight is assigned; the calculated difference in Path B is relatively low, and the weight is also low. The system sets a threshold to filter out paths with higher weights, such as Path A, as target traversal paths, and excludes paths with lower weights to reduce redundant information for subsequent analysis.

[0058] Step 2042: traverse the advertising data along the target traversal path, determine the relationship edges between the entities corresponding to the nodes at each level in the advertising knowledge graph, and construct the association relationship matrix between the nodes at each level based on the relationship strength and semantic information of the relationship edges.

[0059] Furthermore, the advertising analysis system traverses the advertising delivery data along the target traversal path, and during the traversal process, determines the relationship edges between the entities corresponding to the nodes at each level in the advertising delivery knowledge graph. For example, for the "X Music Platform" node and the "X Music Platform Delivery Time" node, find the relationship edge between the "X Music Platform" entity and the "X Music Platform Delivery Time" entity in the knowledge graph. Then, evaluate the relationship strength of the relationship edge, which can be determined based on factors such as the frequency of relationship occurrence and the closeness of related data. At the same time, combined with the semantic information of the relationship edge, the relationship strength and semantic information are quantified to construct an association relationship matrix between nodes at each level, where the elements in the matrix represent the degree of association and relationship type between different nodes, and intuitively present the association structure between nodes.

[0060] Continuing with the above example, following the target traversal path "Online Education Course Promotion Project → Online Education Market Promotion → X-audio Platform → X-audio Platform Educational Short Video Promotion → X-audio Platform Delivery Time," the advertising analysis system determines that the relationship edge between the "X-audio Platform" entity and the "X-audio Platform Educational Short Video Promotion" entity is "Provide Short Video Promotion Channel." This relationship appears frequently in past data, and the relationship strength is set to a high value. The relationship edge between the "X-audio Platform Educational Short Video Promotion" entity and the "X-audio Platform Delivery Time" entity is "Deliver Short Video Ads at Specific Times." The relationship strength is determined to be medium based on actual delivery performance data. These relationship strengths and semantic information are quantified to construct an association matrix. In the matrix, the elements corresponding to "X-audio Platform" and "X-audio Platform Educational Short Video Promotion" represent a strong association and relationship semantics between the two. The elements corresponding to "X-audio Platform Educational Short Video Promotion" and "X-audio Platform Delivery Time" represent a medium association and corresponding semantics, clearly demonstrating the associations between nodes at each level.

[0061] Step 2043: For the advertising delivery data corresponding to the nodes at each level, based on the semantic information changes of the entities corresponding to the nodes at each level in the advertising delivery knowledge graph at different time points, determine the data change trend vector between the nodes at each level.

[0062] Furthermore, for the advertising data corresponding to nodes at each level, the advertising analysis system focuses on the semantic information changes of the entities corresponding to each node in the advertising knowledge graph at different time points. This embodiment of the present invention determines the data change trends between nodes at each level by analyzing the evolution of entity semantic information over time (such as the increase or decrease of keywords, the shift in themes, etc.). The data change trends are quantified and converted into data change trend vectors. The dimensions and element values ​​of the vectors reflect the direction and degree of data change, thus clearly presenting the dynamic changes of the data along the time dimension.

[0063] Continuing with the example of the "X Music Platform Delivery Time" node, the corresponding "X Music Platform Delivery Time" entity in the advertising delivery knowledge graph changes its semantic information over time. In the early days, the delivery time was mainly concentrated between 7 and 9 pm on weekdays; after a period of time, the delivery time between 2 and 4 pm on weekends was added. The advertising analysis system analyzes these changes in semantic information and combines them with the corresponding advertising delivery data (such as ad exposure and click-through rate in different time periods) to determine the data change trend. This change trend is quantified into a data change trend vector. For example, one dimension of the vector represents the change trend of exposure over time, and the element value is determined according to the increase or decrease in exposure; the other dimension represents the change trend of click-through rate, and the element value is also set according to the change in click-through rate, thereby forming a complete data change trend vector.

[0064] Step 2044 , based on the association relationship matrix between nodes at each level and the data change trend vector, a fusion is performed to obtain hierarchical effect information of the advertisement delivery.

[0065] Furthermore, the advertising analysis system fuses the relationship matrix between nodes at each level with the data change trend vector. This embodiment of the present invention combines the node relationships and data change trends through a specific fusion method (e.g., integrating matrix elements with vector elements), forming a comprehensive information set. This information set is organized and structured, categorized by advertising delivery platform, delivery factors, and other hierarchical levels to obtain hierarchical advertising effect information, clearly displaying the advertising effectiveness at different levels and dimensions.

[0066] Continuing with the above example, the association matrix and data change trend vector related to the "X Music Platform" are merged. The association elements between nodes such as "X Music Platform" and "X Music Platform Educational Short Video Promotion" and "X Music Platform Delivery Time" in the association matrix are integrated with the corresponding data change elements in the data change trend vector, such as exposure and click-through rate. For example, the strong association between "X Music Platform" and "X Music Platform Educational Short Video Promotion" is combined with the increasing exposure trend driven by short video promotion to form a comprehensive information unit. All relevant information units are organized and categorized by "X Music Platform" and delivery factors (such as delivery time and promotion format) to obtain hierarchical performance information for advertising on the "X Music Platform." The same method is applied to other platforms, ultimately summarizing hierarchical performance information for the entire advertising campaign, comprehensively presenting the impact of each platform and factor on the advertising effectiveness.

[0067] The embodiments of the present invention can deeply explore the correlation relationship between nodes at all levels, accurately grasp the data change trend, effectively integrate the correlation relationship and data change trend, and form clearly layered advertising effect information. Therefore, it can comprehensively cover the effects of different advertising delivery platforms and various delivery elements in different time dimensions, provide a basis for the optimization and adjustment of advertising delivery strategies, thereby adapting to the complex and changeable advertising delivery environment, and improving the timeliness and effectiveness of advertising delivery strategy adjustments.

[0068] In one embodiment, steps 301 to 304 are described as follows:

[0069] Step 301: Determine the entity level of each entity in the advertising delivery knowledge graph in the advertising delivery structure tree based on the association mapping relationship.

[0070] Optionally, the advertising analysis system analyzes each entity in the advertising delivery knowledge graph based on the association mapping relationship, wherein the association mapping relationship clarifies the correspondence rules between the knowledge graph entities and the advertising delivery structure tree nodes. Therefore, the corresponding position of each entity in the advertising delivery structure tree is found through these rules to determine its entity hierarchy. For example, if the "Xyin Platform" entity in the knowledge graph corresponds to the "Xyin Platform" sub-node under the "Online Education Course Advertising Delivery Activity" root node in the structure tree, then the hierarchy of the "Xyin Platform" entity is the first-level sub-node hierarchy; if the "Xyin Platform Delivery Budget" entity in the knowledge graph corresponds to the sub-node under the "Xyin Platform" sub-node, its hierarchy is the second-level sub-node hierarchy.

[0071] Continuing in the "Online Education Course Advertising Campaign" scenario, the advertising analysis system analyzes the entities in the advertising knowledge graph. The "Online Education Institution" entity corresponds to the subject represented by the root node "Online Education Course Advertising Campaign" in the advertising structure tree through an associated mapping relationship, and its level is the root node level; the "X Music Platform" entity corresponds to the "X Music Platform" sub-node under the root node in the structure tree, and its level is determined to be the first-level sub-node level; the "X Music Platform Delivery Time" entity under the "X Music Platform" corresponds to the sub-node under the "X Music Platform" sub-node in the structure tree, and its level is the second-level sub-node level. In this way, the system determines the entity level in the advertising structure tree for each entity in the knowledge graph.

[0072] Step 302: Based on the relationships between entities in the advertising knowledge graph and the entity hierarchy of each entity, a relationship hierarchy matrix is ​​constructed. Matrix elements in the relationship hierarchy matrix represent the association characteristics of the relationships between entities at the corresponding entity hierarchy in the advertising structure tree.

[0073] Furthermore, the advertising analysis system constructs a relationship hierarchy matrix based on the relationships between entities in the advertising knowledge graph and the determined entity hierarchy of each entity. For any two entities that have a relationship in the knowledge graph, the correlation characteristics of their corresponding entity hierarchies in the advertising structure tree are analyzed. Correlation characteristics include whether the hierarchies are the same, the size of the hierarchical gap, the logical relationship between the hierarchies, etc. These correlation characteristics are quantified and represented as matrix elements in the relationship hierarchy matrix. For example, if two entities have the same hierarchy in the structure tree, the matrix element can be assigned a value of 1; if the hierarchy differs by one level, the matrix element is assigned a value of -1; if there is an inclusion relationship between the hierarchies, the corresponding numerical value is assigned according to the specific situation, thereby constructing a complete relationship hierarchy matrix, which intuitively displays the correlation between the relationship between entities and the hierarchy of the structure tree.

[0074] Continuing in the advertising delivery knowledge graph, the "X Music Platform" and "X Music Platform Delivery Time" entities have a "platform includes delivery time settings" relationship. The "X Music Platform" entity level is a first-level child node level, and the "X Music Platform Delivery Time" entity level is a second-level child node level. The levels differ by one level. The advertising analysis system assigns a value of -1 to the elements corresponding to the relationship between these two entities in the relationship hierarchy matrix. For another example, there is a relationship between the "X Xin Platform Advertising Platform" and the "X Xin Platform Copy Content" entities, and their hierarchical relationships in the structure tree are similar. The corresponding elements in the matrix are also assigned a value of -1. For "Online Education Institution" and "X Music Platform", "Online Education Institution" is the root node level, and "X Music Platform" is the first-level child node level. There is a relationship between the subject and the delivery platform. According to the hierarchical and relationship characteristics, the corresponding values ​​are assigned in the matrix. By analyzing all entity relationships in the knowledge graph, a complete relationship hierarchy matrix is ​​constructed.

[0075] Step 303: traverse the advertising placement structure tree from the root node. If the target node traversed in the advertising placement structure tree is a node corresponding to the mapping entity in the advertising placement knowledge graph, a hierarchical path is constructed based on the target node.

[0076] Furthermore, in the advertising delivery structure tree, the advertising analysis system traverses from the root node "Online Education Course Advertising Delivery Activity". During the traversal process, when the target node encountered is a node corresponding to the mapping entity in the advertising delivery knowledge graph, a hierarchical path is constructed based on the target node. The hierarchical path starts from the root node, records each node passed through, until the target node, and clearly presents the hierarchical position and subordinate relationship of the node in the structure tree. Continuing with the above embodiment, traversal starts from the root node "Online Education Course Advertising Delivery Activity" of the advertising delivery structure tree. When traversing to the "X Music Platform" node, since the "X Music Platform" node corresponds to the "X Music Platform" entity in the advertising delivery knowledge graph, with the "X Music Platform" node as the end point, a hierarchical path is constructed: "Online Education Course Advertising Delivery Activity → X Music Platform". Continue traversing, and when you encounter the "Delivery Time" sub-node under the "X Music Platform" node, which corresponds to the "X Music Platform Delivery Time" entity in the knowledge graph, construct a new hierarchical path: "Online Education Course Advertising Delivery Activity → X Music Platform → Delivery Time", and construct corresponding hierarchical paths for all nodes in the structure tree that are mapped to the knowledge graph entities.

[0077] Step 304 , based on the relationship hierarchy matrix combined with the hierarchical path and the relationship path in the advertising delivery knowledge graph, the delivery effect is inferred to obtain the potential effect information of the advertising delivery.

[0078] Furthermore, the advertising analysis system infers the effect of advertising delivery based on the relationship hierarchy matrix combined with the hierarchical path and the relationship path in the advertising delivery knowledge graph to obtain potential effect information of advertising delivery, as specifically described in steps 3041 to 3043.

[0079] The embodiment of the present invention can sort out the relationship between entities in the advertising delivery knowledge graph and the hierarchy of the advertising delivery structure tree, and construct a matrix that reflects the entity relationship and the hierarchy association, so as to construct a hierarchical path by traversing the structure tree, combine the relationship hierarchy matrix and the knowledge graph relationship path, deeply analyze the relationship between each element, and infer the potential effect information of advertising delivery, thereby covering the effect improvement direction that may be brought about by different platforms and different combinations of delivery elements, which is helpful to plan and optimize advertising delivery strategies in advance, thereby adapting to the complex and changing advertising delivery environment, and improving the timeliness and effectiveness of advertising delivery strategy adjustments.

[0080] In one embodiment, steps 3041 to 3043 are described as follows:

[0081] Step 3041: If it is determined based on the relationship hierarchy matrix that the hierarchical path matches the relationship path, the hierarchical path and the relationship path are fused to obtain a fused path.

[0082] Optionally, the advertising analysis system analyzes and determines hierarchical paths and relational paths based on a relationship hierarchy matrix. The hierarchical path is the node path constructed in the advertising placement structure, and the relational path is the relationship connection between entities in the advertising placement knowledge graph. Therefore, the hierarchical path and the relational path are compared to determine whether they match. If they match, meaning the node hierarchical relationships in the hierarchical path and the relationships between entities in the relational path are logically and structurally consistent, the hierarchical path and the relational path are fused to integrate their information and produce a fused path. The fused path integrates the hierarchical information of the structure tree and the relationship information of the knowledge graph.

[0083] Continuing in the "Online Education Course Advertising Campaign", the hierarchical path "Online Education Course Advertising Campaign → X-Music Platform → Delivery Time" is constructed, and the relationship path "Online Education Course Promotion Project → X-Music Platform → X-Music Platform Delivery Time Setting" in the advertising delivery knowledge graph. From a structural and logical point of view, the nodes in the hierarchical path correspond to the entities in the relationship path, and the hierarchical relationship and the entity relationship are consistent. After determining that the two match based on the relationship hierarchy matrix, the two paths are fused to obtain the fused path: "Online Education Course Advertising Campaign (Online Education Course Promotion Project) → X-Music Platform (X-Music Platform) → Delivery Time (X-Music Platform Delivery Time Setting)". In the fused path, the corresponding entity information in the knowledge graph is in brackets, realizing the integration of the structure tree hierarchical information and the knowledge graph relationship information.

[0084] Step 3042: For each path in the fused path, determine the delivery effect inference rule of the fused path based on the path characteristics of the path and the potential impact of each node in the path on the delivery effect.

[0085] Furthermore, the advertising analysis system analyzes the path characteristics of each resulting fused path, including path length, node type, and the node's importance within the structure tree and knowledge graph. It also assesses the potential impact of each node on the effectiveness of the advertising campaign, with the impact determined based on historical data performance of the advertising element represented by the node, industry experience, and other factors.

[0086] Furthermore, the advertising analysis system integrates path characteristics and the potential impact of nodes to develop inference rules for delivery effectiveness. For example, if the path is short and contains a key delivery factor node, and this node has a high degree of influence on delivery effectiveness, the inference rule can be set to focus on this node and optimize the related delivery strategy. If there are multiple interconnected nodes in the path that have a synergistic impact on delivery effectiveness, the inference rule can be set to adjust the relationship between these nodes to improve delivery effectiveness.

[0087] Continuing with the example of the fusion path "Online Education Course Advertising Campaign (Online Education Course Promotion Project) → Xyin Platform (Xyin Platform) → Delivery Time (Xyin Platform Delivery Time Setting)", the advertising analysis system analyzes its path characteristics. The path is of moderate length and includes the main body of the advertising campaign, the delivery platform, and the key delivery element "delivery time" node. By analyzing historical data and industry experience, the "delivery time" node has a high degree of influence on the advertising delivery effect of the Xyin platform, and the "Xyin Platform" node is also crucial as a core delivery platform. Based on this, the delivery effect inference rules are determined: focus on the "delivery time" node, and further refine and optimize the delivery time arrangement of "online education course advertising" on the Xyin platform based on the active time period data of Xyin platform users; at the same time, evaluate the synergistic relationship between the "Xyin Platform" and "delivery time" nodes, and enhance the effect of both on the advertising delivery effect by adjusting the delivery time strategy.

[0088] Step 3043: Based on the delivery effect inference rule, the delivery effect of the fusion path is inferred to obtain potential effect information of the advertisement delivery.

[0089] Furthermore, the advertising analysis system adjusts and simulates the nodes and relationships in the fusion path based on the advertising effect inference rules, predicts the changes in advertising effect under different operations, and thus obtains the potential effect information of advertising.

[0090] For example, based on inference rules, the advertising parameters of a particular node are adjusted. The impact of this adjustment on other nodes and the overall advertising performance, as propagated through the relationships in the fusion path, is analyzed to identify potential areas for improvement or potential issues. Continuing with the above-described embodiment, based on the determined advertising performance inference rules, the advertising analysis system performs inference on the fusion path "Online Education Course Advertising Campaign (Online Education Course Promotion Project) → Xyin Platform (Xyin Platform) → Advertising Time (Xyin Platform Advertising Time Settings)." The advertising analysis system simulates adjusting the advertising time to a specific time period with higher user activity on the Xyin Platform. Based on the relationships and inference rules between the nodes in the fusion path, the system analyzes how this adjustment affects ad impressions, user click-through rates, and the conversion rate of the entire "Online Education Course Advertising Campaign" on the Xyin Platform. The inference concludes that, if the new advertising time strategy is implemented, the click-through rate of ads on the Xyin Platform is expected to increase by 15%, and the conversion rate of the overall advertising campaign on the Xyin Platform is expected to increase by 10%. These predicted results provide information on the potential effectiveness of the advertising campaign.

[0091] The embodiment of the present invention can effectively integrate the hierarchical information of the advertising delivery structure tree with the relationship information of the advertising delivery knowledge graph to form a fusion path containing rich information. Therefore, the delivery effect inference rules determined based on the characteristics of the fusion path and the node influence provide a clear logical basis for the analysis of the advertising delivery effect, and can deeply explore the potential effects that may be brought about by different combinations of advertising delivery elements and strategy adjustments, and obtain targeted and forward-looking potential advertising delivery effect information, so as to provide accurate guidance for the optimization of advertising delivery strategies, thereby adapting to the complex and changing advertising delivery environment and improving the timeliness and effectiveness of advertising delivery strategy adjustments.

[0092] In one embodiment, steps 401 to 404 are described as follows:

[0093] Step 401 : For each advertisement delivery platform, correlation analysis is performed based on the first advertisement feature corresponding to the hierarchical effect information and the second advertisement feature corresponding to the potential effect information, and a feature correlation matrix is ​​constructed.

[0094] Optionally, for each advertising delivery platform, the advertising analysis system extracts corresponding first advertising features from the hierarchical effect information, such as the platform's actual exposure, click-through rate, conversion rate and other actual delivery effect-related features; and extracts corresponding second advertising features from the potential effect information, such as potential exposure growth space, potential conversion rate improvement points and other features derived based on reasoning.

[0095] Furthermore, the advertising analysis system analyzes the correlation between these first advertising features and the second advertising features, including the causal relationship between the features, the degree of mutual influence, etc., and quantifies these correlations to construct a feature correlation matrix, in which the elements in the matrix reflect the correlation strength and correlation nature between different features, thereby clearly presenting the intrinsic connection between the advertising features of each platform.

[0096] Continuing with the "Online Education Course Advertising Campaign," for the "Xin Platform," the advertising analysis system extracts the first ad feature from the hierarchical performance information: current ad impressions are 15,000 per day, with a click-through rate of 5% and a conversion rate of 3%. The second ad feature is extracted from the potential performance information: if the delivery time is optimized, the potential impressions can be increased to 20,000 per day, and the potential conversion rate is expected to increase to 5%. The analysis found a correlation between the current click-through rate and the potential conversion rate. Optimizing the ad content to increase the current click-through rate may also help increase the potential conversion rate. This correlation is quantified and entered into the corresponding position in the feature correlation matrix. Similarly, the "Xin Platform" and "Xdu Platform" are analyzed, extracting their respective first and second ad features and determining the correlation between them, thus constructing a complete feature correlation matrix for each platform.

[0097] Step 402: Perform effect difference analysis based on the first advertisement feature, the second advertisement feature, and the feature correlation matrix to obtain platform effect difference information.

[0098] Furthermore, based on the extracted first and second ad features and the constructed feature correlation matrix, the advertising analysis system analyzes the effectiveness differences across various advertising delivery platforms. Specifically, the system compares the first ad features across different platforms to understand the differences in actual current delivery effectiveness; and compares the second ad features to analyze the differences in potential delivery effectiveness across platforms. Furthermore, the feature correlation matrix is ​​used to consider the impact of inter-feature correlations on effectiveness differences. Through this comprehensive analysis, the differences in actual and potential effectiveness across various advertising delivery platforms are determined, generating information on platform effectiveness differences.

[0099] Continuing with the above embodiment, the advertising analysis system compares the first advertising features of the three platforms, "Xyin Platform", "Xxin Platform" and "Xdu Platform", and finds that "Xyin Platform" has a high exposure volume but a relatively low conversion rate, "Xxin Platform" has a high conversion rate but limited exposure, and "Xdu Platform" has a unique performance in keyword search traffic conversion. Comparing the second advertising features, "Xyin Platform" has a large room for potential exposure improvement, "Xxin Platform" has obvious potential for improving potential conversion rate by optimizing targeted population strategies, and "Xdu Platform" can be expected to improve potential effects after optimizing keyword settings. Combined with the feature correlation matrix, the impact of the correlation between the features of each platform on the effect is analyzed, such as the correlation between the click-through rate and potential conversion rate of "Xyin Platform" affects the direction of its overall effect improvement. Finally, the advertising analysis system obtains platform effect difference information, clarifying that "Xyin Platform" currently focuses on exposure and potential conversion optimization; "Xxin Platform" currently focuses on conversion and potential exposure expansion; "Xdu Platform" needs to balance differences such as keyword traffic and conversion.

[0100] Step 403: Identify potential opportunities and potential risks of each advertising delivery platform based on the potential effect information.

[0101] Furthermore, the advertising analysis system conducts in-depth analysis of each advertising platform based on potential effect information to identify potential opportunities and risks. For potential opportunities, the system looks for directions and points that can significantly improve advertising effectiveness through reasonable adjustments to advertising strategies and optimization of advertising elements. For example, if a specific user group on a platform is not yet fully covered, there is an opportunity to expand the audience and improve effectiveness. For potential risks, the system focuses on factors that may lead to a decline in advertising effectiveness, such as policy changes that may affect the advertising display rules of a platform, thereby affecting the effectiveness of advertising. Through comprehensive analysis, the system clearly identifies the potential opportunities and potential risks of each platform.

[0102] Continuing to analyze the potential performance of the "Xin Platform," the advertising analysis system discovered that the platform's newly launched educational livestreaming promotion feature is still in its developmental stages. If online education course ads can be promptly included in livestreaming promotions, leveraging the interactivity and real-time nature of livestreaming, they could attract more user attention, presenting a potential opportunity for the "Xin Platform." At the same time, Xin Platform users are increasingly demanding creative content from advertising. If the advertising analysis system fails to optimize ad content in a timely manner, user resistance to ads could increase, leading to lower click-through and conversion rates, representing a potential risk. For the "Xin Platform," the potential opportunity lies in Xin's recent opening of more ad placements, which could increase ad exposure. A potential risk lies in Xin's user privacy policy adjustments, which could affect the accuracy of ad targeting. For the "Xdu Platform," the potential opportunity lies in the increasing search volume for emerging education keywords, which could allow for increased traffic by expanding into related keywords. A potential risk lies in the increased keyword bidding by competitors, which could lead to higher advertising costs. Through this analysis, the advertising analysis system identifies both potential opportunities and risks for each platform.

[0103] Step 404 : Based on the platform effect difference information, potential opportunities, and potential risks of each advertising delivery platform, a delivery effect decision analysis is performed to obtain delivery optimization information for multi-platform advertising delivery.

[0104] Furthermore, the advertising analysis system performs a delivery effect decision analysis based on the platform effect difference information, potential opportunities and potential risks of each advertising delivery platform to obtain delivery optimization information for multi-platform advertising delivery, as specifically described in steps 4041 to 4044.

[0105] The embodiment of the present invention constructs a feature correlation matrix to clearly sort out the internal connections between the advertising features of each platform, analyzes the effect differences, identifies potential opportunities and risks, and then makes comprehensive decisions based on this information, ultimately obtaining highly targeted delivery optimization information. This allows the delivery optimization information to cover multiple aspects such as budget allocation, strategy adjustment, and risk prevention and control, making the advertising delivery strategy more scientific and reasonable, thereby adapting to the complex and changing advertising delivery environment and improving the timeliness and effectiveness of the adjustment of the advertising delivery strategy.

[0106] In one embodiment, steps 4041 to 4044 are described as follows:

[0107] Step 4041 , for each advertising delivery platform, strategy screening is performed based on the advertising delivery goal combined with platform effect difference information, potential opportunities and potential risks to determine a preliminary delivery strategy.

[0108] Optionally, for each advertising platform, the advertising analysis system combines advertising objectives (such as increasing brand awareness, increasing course enrollment, and boosting user activity) with information on platform performance differences, potential opportunities, and potential risks to comprehensively assess each platform's strengths and weaknesses in achieving specific objectives, as well as the impact of potential opportunities and risks on achieving those objectives. For example, if the advertising goal is to increase course enrollment, for platforms with low actual conversion rates but significant potential for improvement, strategies such as optimizing ad content and adjusting delivery timing may be considered. For platforms where potential risks could affect the achievement of these objectives, risk mitigation strategies are identified and a preliminary delivery strategy is determined for each platform.

[0109] Continuing with the "Online Education Course Advertising Campaign," the advertising goal is to increase course enrollment by 30% within one month. For the "Xyin Platform," platform performance differentials indicate a low current conversion rate. Potential performance data suggests optimizing ad timing and ad content could improve conversion rates, but there's also the potential risk of increased user expectations for creative content. The advertising analytics system has identified a preliminary advertising strategy for the "Xyin Platform": adjusting ad delivery times to 7-10 PM, when users are most active; investing resources in optimizing ad video content to increase interest and interactivity; and assigning dedicated personnel to monitor user feedback and adjust advertising strategies promptly to address potential risks. For the "Xinxin Platform," given its high conversion rate but limited exposure and potential opportunities for new ad placements, the initial advertising strategy is to increase the advertising budget and leverage the new placements to expand exposure; optimize ad copy to highlight the course's strengths and attract more clicks. For the "Xdu Platform," given its keyword-to-traffic conversion characteristics, the potential for increased search volume for emerging education keywords, and the potential risk of competitive bidding, the initial advertising strategy is to increase advertising for emerging education keywords; and develop a flexible bidding strategy that dynamically adjusts bids based on competitor performance.

[0110] Step 4042 : For any two first delivery strategies and second delivery strategies in the preliminary delivery strategies, a synergy analysis is performed based on a first strategy feature corresponding to the first delivery strategy and a second strategy feature corresponding to the second delivery strategy to obtain a strategic synergy degree between the two delivery strategies.

[0111] Furthermore, the advertising analysis system extracts the first strategy features corresponding to the first delivery strategy (such as the ad delivery time, budget, content, and other related features involved in the strategy) and the second strategy features corresponding to the second delivery strategy for any two strategies in the preliminary delivery strategy (the first delivery strategy and the second delivery strategy). Furthermore, the advertising analysis system analyzes the interaction between these strategy features to determine whether the two strategies can promote each other and synergize in achieving the advertising delivery goals. For example, if one strategy is to increase the advertising budget to expand exposure, and the other strategy is to optimize the ad content to increase click-through rate, if increasing exposure allows more users to see the optimized ad content, thereby improving the conversion rate, it means that the two strategies have a high degree of synergy. Therefore, this synergy is quantified to obtain the strategic synergy degree between the two delivery strategies, with higher values ​​indicating stronger synergy.

[0112] Continuing with the initial delivery strategy, the "Xinyin Platform" adopted the following strategies: "Adjusting ad delivery time to 7-10 PM, when users are most active" (the first delivery strategy) and "Investing resources to optimize ad video content to increase interest and interactivity" (the second delivery strategy). The first strategy's first characteristics included the new delivery time period, while the second strategy's second characteristics included the optimized ad content style and interactive format. It was found that delivering optimized ad content during active user hours enabled more users to see high-quality ads, increasing user dwell time and click-through rate (CTR), a mutually reinforcing relationship. By analyzing this facilitating relationship, this was quantified as strategy synergy, set at a high value of 0.8. For example, the "Xinxin Platform" strategies of "Increasing advertising budget and leveraging new placements to expand exposure" and "Optimizing ad copy to highlight the advantages of the course to attract more clicks" demonstrated that increased exposure enabled the optimized copy to reach more users, thereby increasing click-through rates. For example, the analysis determined a strategy synergy of 0.7.

[0113] Step 4043 : Based on the dynamic environment factors of multiple platforms and the strategic synergy between any two delivery strategies, the adaptability of each delivery strategy in the dynamic environment is determined.

[0114] Furthermore, the advertising analysis system considers dynamic environmental factors of multiple platforms, such as changes in market trends, adjustments to competitor strategies, changes in user demand, updates to platform policies, etc., and combines the strategic synergy between any two delivery strategies to evaluate the adaptability of each delivery strategy in a dynamic environment. Optionally, an embodiment of the present invention analyzes the impact of dynamic environmental factors on each strategy, and whether the synergy between strategies can enhance the ability to respond to environmental changes. For example, if the market trend shifts to focus more on the interactivity of video content, and the delivery strategy of a certain platform includes optimizing advertising video content to increase interactivity, and this strategy has a high degree of synergy with other strategies, then the adaptability of this strategy in a dynamic environment is relatively high. This adaptability is quantified to obtain the adaptability of each delivery strategy in a dynamic environment.

[0115] Continuing with the above example, recent trends in the online education market show that users are more inclined to watch live courses, while competitors have increased their live broadcast promotion efforts on the "Xyin Platform." Among the initial delivery strategies of the "Xyin Platform," namely, "adjusting the advertising delivery time to 7-10 p.m. when users are active," "investing resources to optimize advertising video content, increase interest and interactivity," and "arranging dedicated personnel to monitor user feedback and adjust advertising strategies in a timely manner to address potential risks," the strategy of "investing resources to optimize advertising video content, increase interest and interactivity" is consistent with market trends, and this strategy has a high degree of strategic synergy with the "adjusting advertising delivery time" strategy, and can better display highly interactive advertising content during user active time periods. The advertising analysis system comprehensively considers dynamic environmental factors and strategic synergy, and determines that the strategy of "investing resources to optimize advertising video content, increase interest and interactivity" has a higher adaptability in dynamic environments, which is set to 0.9; the strategy of "adjusting advertising delivery time to 7-10 p.m. when users are active" has an adaptability of 0.8. For the "Xin Platform", if Xin launches a new privacy policy that affects targeted advertising, the strategy of "optimizing advertising copy, highlighting the advantages of courses to attract more user clicks" will be less affected, and has a certain synergy with the strategy of "increasing advertising budget and using new display positions to expand exposure". The fitness of the "optimizing advertising copy" strategy is determined to be 0.7, and the fitness of the "increasing advertising budget" strategy is determined to be 0.6.

[0116] Step 4044: Perform a delivery effect decision analysis based on the adaptability of each delivery strategy in a dynamic environment to obtain delivery optimization information for multi-platform advertising.

[0117] Furthermore, the advertising analysis system performs a comprehensive delivery effect decision analysis based on the adaptability of each delivery strategy in a dynamic environment. The embodiment of the present invention gives priority to implementing strategies with high adaptability and adjusts the resource allocation and execution priority of the strategy according to the adaptability.

[0118] For strategies with low adaptability, the system considers whether they need to be optimized, adjusted, or abandoned. At the same time, it integrates the strategies of each platform to develop an overall multi-platform advertising optimization plan, including budget allocation, strategy combinations, execution schedules, and other content for each platform. This generates optimized information for multi-platform advertising to maximize advertising effectiveness in a dynamic environment.

[0119] Continuing with the above example, a decision analysis was conducted on the "online education course advertising campaign" based on the adaptability of each platform's delivery strategy in a dynamic environment. For the "Xin Platform," since the strategy of "investing resources to optimize advertising video content and increase fun and interactivity" had the highest adaptability (0.9), the decision was made to increase resource investment in this strategy, increasing the number of video production team members and budget. The strategy of "adjusting advertising delivery time to 7-10 pm when users are active" had a adaptability of 0.8 and was executed as planned with continuous monitoring of the results. For the "Xin Platform," the strategy of "optimizing advertising copy and highlighting the advantages of the course to attract more user clicks" had a adaptability of 0.7 and was implemented as the key strategy. At the same time, based on the adaptability, the budget investment for the strategy of "increasing advertising delivery budget and utilizing new display locations to expand exposure" (adaptability 0.6) was appropriately reduced. Based on the situation of each platform, the final delivery optimization information was determined: 60% of the "Xyin Platform" budget was used to optimize the advertising video content, 30% was used to adjust the delivery time, and 10% was used to monitor feedback; 70% of the "Xinxin Platform" budget was used to optimize the advertising copy, and 30% was used for limited exposure expansion; each platform strategy was executed in an orderly manner according to priority and time nodes to achieve the goal of increasing course registrations by 30% and adapt to changes in the dynamic market environment.

[0120] The embodiments of the present invention can fully consider the advertising delivery goals, platform characteristics, strategy synergy and dynamic environmental factors, from screening the preliminary delivery strategy, to analyzing the strategy synergy, determining the adaptability of the strategy in a dynamic environment, and finally making scientific decisions based on the adaptability, to obtain comprehensive and targeted multi-platform advertising delivery optimization information, so that the optimization information ensures that the advertising delivery strategy not only fits the actual situation and potential opportunities of each platform, but also maintains good adaptability and synergy in a complex and changing market environment, adapts to the complex and changing advertising delivery environment, and improves the timeliness and effectiveness of the adjustment of the advertising delivery strategy.

[0121] Furthermore, the multi-platform advertising delivery effect analysis system based on artificial intelligence provided by the present invention is described below. The multi-platform advertising delivery effect analysis system based on artificial intelligence described below and the multi-platform advertising delivery effect analysis method based on artificial intelligence described above can be referenced to each other.

[0122] Reference Figure 2 , Figure 2It is a structural diagram of the multi-platform advertising delivery effect analysis system based on artificial intelligence provided by the present invention. The multi-platform advertising delivery effect analysis system based on artificial intelligence includes.

[0123] Construction module 210 is used to construct an advertising placement structure tree and an advertising placement knowledge graph; the advertising placement structure tree is constructed by taking a preset advertising campaign as a root node, different advertising placement platforms as child nodes under the root node, and advertising placement elements of different advertising placement platforms as different hierarchical nodes as child nodes; the advertising placement knowledge graph is constructed by taking different advertising placement platforms and advertising placement entities of different advertising placement platforms as entities, and taking relationships between entities as edges;

[0124] The effect trend analysis module 220 is used to start from the root node of the advertising placement structure tree, combine the semantic information of each node mapped to the advertising placement knowledge graph by the association mapping relationship, traverse the advertising placement data along different paths, analyze the association relationships and data change trends between nodes at each level, and obtain hierarchical effect information of advertising placement; the association mapping relationship represents the mapping relationship between the entity in the advertising placement knowledge graph and the node in the advertising placement structure tree;

[0125] The effect inference module 230 is used to perform advertising effect inference based on the relationship between entities in the advertising knowledge graph and the hierarchy of entities mapped to the advertising structure tree in combination with the association mapping relationship to obtain potential effect information of the advertising;

[0126] The effect decision analysis module 240 is used to perform delivery effect decision analysis based on the hierarchical effect information and potential effect information to obtain delivery optimization information for multi-platform advertising delivery.

[0127] By constructing a multi-platform advertising delivery structure tree, the embodiment of the present invention can clearly present the hierarchical architecture of multi-platform advertising delivery, intuitively display the inherent correlation and data change trends of advertising delivery on each platform, and make the analysis no longer limited to simple matching under fixed rules. Generating an advertising delivery knowledge graph and performing semantic reasoning can dig out the potential complex relationships and semantic information between entities in advertising delivery, making up for the defect that fixed rules cannot incorporate new factors. Therefore, the association mapping between the structure tree and the knowledge graph and the subsequent comprehensive analysis can comprehensively and deeply analyze the advertising delivery effect from the two dimensions of hierarchy and semantics, and promptly discover new factors and potential optimization space that affect the advertising delivery effect, thereby generating more accurate and effective optimization suggestions, adapting to the complex and changing advertising delivery environment, and improving the timeliness and effectiveness of advertising delivery strategy adjustments.

[0128] See also Figure 3 , Figure 3 This is a diagram of an embodiment of an electronic device provided by an embodiment of the present invention. Figure 3As shown, an embodiment of the present invention provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor 320. When the processor 320 executes the computer program 311, the following steps are implemented:

[0129] Construct an advertising structure tree and an advertising knowledge graph; the advertising structure tree is constructed with a preset advertising campaign as the root node, different advertising platforms as child nodes under the root node, and advertising elements of different advertising platforms as different child nodes; the advertising knowledge graph is constructed with different advertising platforms and advertising entities of different advertising platforms as entities, and the relationships between entities as edges;

[0130] Starting from the root node of the advertising structure tree, combined with the semantic information of each node mapped to the advertising knowledge graph by the association mapping relationship, the advertising data is traversed along different paths, and the association relationships and data change trends between nodes at each level are analyzed to obtain hierarchical effect information of advertising. The association mapping relationship represents the mapping relationship between entities in the advertising knowledge graph and nodes in the advertising structure tree.

[0131] Based on the relationship between entities in the advertising knowledge graph, combined with the association mapping relationship, the advertising effect is inferred at the level of each entity mapped in the advertising structure tree to obtain the potential effect information of the advertising;

[0132] Based on hierarchical effect information and potential effect information, we conduct delivery effect decision analysis to obtain delivery optimization information for multi-platform advertising.

[0133] See also Figure 4 , Figure 4 Detailed description of an embodiment of a computer-readable storage medium provided by an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 400 on which a computer program 311 is stored. When the computer program 311 is executed by a processor, the following steps are implemented:

[0134] Construct an advertising structure tree and an advertising knowledge graph; the advertising structure tree is constructed with a preset advertising campaign as the root node, different advertising platforms as child nodes under the root node, and advertising elements of different advertising platforms as different child nodes; the advertising knowledge graph is constructed with different advertising platforms and advertising entities of different advertising platforms as entities, and the relationships between entities as edges;

[0135] Starting from the root node of the advertising structure tree, combined with the semantic information of each node mapped to the advertising knowledge graph by the association mapping relationship, the advertising data is traversed along different paths, and the association relationships and data change trends between nodes at each level are analyzed to obtain hierarchical effect information of advertising. The association mapping relationship represents the mapping relationship between entities in the advertising knowledge graph and nodes in the advertising structure tree.

[0136] Based on the relationship between entities in the advertising knowledge graph, combined with the association mapping relationship, the advertising effect is inferred at the level of each entity mapped in the advertising structure tree to obtain the potential effect information of the advertising;

[0137] Based on hierarchical effect information and potential effect information, we conduct delivery effect decision analysis to obtain delivery optimization information for multi-platform advertising.

[0138] In another aspect, the present invention further provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can perform the artificial intelligence-based multi-platform advertising effectiveness analysis method provided by the above methods, which includes:

[0139] Construct an advertising structure tree and an advertising knowledge graph; the advertising structure tree is constructed with a preset advertising campaign as the root node, different advertising platforms as child nodes under the root node, and advertising elements of different advertising platforms as different child nodes; the advertising knowledge graph is constructed with different advertising platforms and advertising entities of different advertising platforms as entities, and the relationships between entities as edges;

[0140] Starting from the root node of the advertising structure tree, combined with the semantic information of each node mapped to the advertising knowledge graph by the association mapping relationship, the advertising data is traversed along different paths, and the association relationships and data change trends between nodes at each level are analyzed to obtain hierarchical effect information of advertising. The association mapping relationship represents the mapping relationship between entities in the advertising knowledge graph and nodes in the advertising structure tree.

[0141] Based on the relationship between entities in the advertising knowledge graph, combined with the association mapping relationship, the advertising effect is inferred at the level of each entity mapped in the advertising structure tree to obtain the potential effect information of the advertising;

[0142] Based on hierarchical effect information and potential effect information, we conduct delivery effect decision analysis to obtain delivery optimization information for multi-platform advertising.

[0143] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0144] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0145] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A multi-platform advertising effect analysis method based on artificial intelligence, characterized in that: include: Constructing an advertising placement structure tree and an advertising placement knowledge graph; the advertising placement structure tree is constructed by taking a preset advertising campaign as a root node, different advertising placement platforms as child nodes under the root node, and advertising placement elements of different advertising placement platforms as different hierarchical nodes of its child nodes; the advertising placement knowledge graph is constructed by taking different advertising placement platforms and advertising placement subjects of different advertising placement platforms as entities, and taking relationships between entities as edges; Starting from the root node of the advertising structure tree, combining the semantic information of each node mapped to the advertising knowledge graph by the association mapping relationship, traversing the advertising data along different paths, analyzing the association relationship and data change trend between nodes at each level, and obtaining hierarchical effect information of advertising; The association mapping relationship represents the mapping relationship between the entities in the advertising delivery knowledge graph and the nodes in the advertising delivery structure tree; Based on the relationship between entities in the advertising knowledge graph, combining the association mapping relationship with the hierarchy of each entity mapped in the advertising structure tree, the advertising effect is inferred to obtain potential effect information of the advertising; Performing a delivery effect decision analysis based on the hierarchical effect information and the potential effect information to obtain delivery optimization information for multi-platform advertising; The specific process of determining the potential effect information of the advertisement placement includes: Determine the entity level of each entity in the advertising delivery knowledge graph in the advertising delivery structure tree based on the association mapping relationship; Based on the relationships between entities in the advertising knowledge graph and the entity hierarchy of each entity, a relationship hierarchy matrix is ​​constructed; the matrix elements in the relationship hierarchy matrix represent the association characteristics of the relationships between entities corresponding to the entity hierarchy in the advertising structure tree; In the advertising placement structure tree, traverse from the root node, and if the target node traversed in the advertising placement structure tree is a node corresponding to the mapping entity in the advertising placement knowledge graph, construct a hierarchical path based on the target node; Based on the relationship hierarchy matrix combined with the hierarchical path and the relationship path in the advertising delivery knowledge graph, the delivery effect is inferred to obtain potential effect information of the advertising delivery.

2. The artificial intelligence-based multi-platform advertising effect analysis method according to claim 1 is characterized in that: The performing of delivery effect decision analysis based on the hierarchical effect information and the potential effect information to obtain delivery optimization information for multi-platform advertising delivery includes: For each advertising delivery platform, a correlation analysis is performed based on the first advertising feature corresponding to the hierarchical effect information and the second advertising feature corresponding to the potential effect information, and a feature correlation matrix is ​​constructed; Performing effect difference analysis based on the first advertisement feature, the second advertisement feature, and the feature correlation matrix to obtain platform effect difference information; Identify potential opportunities and potential risks of each advertising delivery platform based on the potential effect information; Based on the platform effect difference information, potential opportunities and potential risks of each advertising platform, the advertising effect decision analysis is carried out to obtain the advertising optimization information for multi-platform advertising.

3. The artificial intelligence-based multi-platform advertising effect analysis method according to claim 2 is characterized in that: The above-mentioned platform effect difference information, potential opportunities and potential risks of each advertising delivery platform are used to perform delivery effect decision analysis to obtain delivery optimization information for multi-platform advertising delivery, including: For each advertising platform, we screen strategies based on advertising goals, combined with information on platform performance differences, potential opportunities, and potential risks, to determine the initial advertising strategy. For any two first delivery strategies and second delivery strategies in the preliminary delivery strategies, performing a synergy analysis based on a first strategy feature corresponding to the first delivery strategy and a second strategy feature corresponding to the second delivery strategy to obtain a strategy synergy degree between the two delivery strategies; Based on the dynamic environmental factors of multiple platforms and the strategic synergy between any two delivery strategies, the adaptability of each delivery strategy in the dynamic environment is determined; Based on the adaptability of each delivery strategy in a dynamic environment, delivery effect decision analysis is performed to obtain delivery optimization information for multi-platform advertising.

4. The method for analyzing the effect of multi-platform advertising based on artificial intelligence according to claim 1, characterized in that: Starting from the root node of the advertising structure tree, combined with the semantic information of each node mapped to the advertising knowledge graph by the association mapping relationship, the advertising data is traversed along different paths, and the association relationship and data change trend between the nodes at each level are analyzed to obtain hierarchical effect information of advertising, including: Starting from the root node of the advertising placement structure tree, locating a first entity associated with the root node in the advertising placement knowledge graph according to the association mapping relationship, and generating an initial traversal path starting from the root node entity based on the similarity and association between the semantic information of the first entity; Finding child nodes corresponding to different advertising delivery platforms in the advertising delivery structure tree along the initial traversal path, finding second entities corresponding to the child nodes in the advertising delivery knowledge graph according to the association mapping relationship, and expanding the initial traversal path based on semantic information of the second entity to obtain an expanded traversal path; For the advertising delivery element nodes of the advertising delivery platform, find the element nodes related to the current path in the advertising delivery structure tree, and fuse the corresponding element semantic information with the corresponding entity semantic information in the advertising delivery knowledge graph to obtain a fused semantic information vector; The advertisement delivery data is traversed based on the expanded traversal path and the fused semantic information vector, and the correlation relationship and data change trend between nodes at each level are analyzed to obtain hierarchical effect information of the advertisement delivery.

5. The artificial intelligence-based multi-platform advertising effect analysis method according to claim 4 is characterized in that: The step of traversing the advertising delivery data based on the expanded traversal path and the fused semantic information vector, analyzing the association relationship and data change trend between nodes at each level, and obtaining hierarchical effect information of advertising delivery includes: Determining a semantic information difference weight of each traversal path based on the total difference of semantic information of each node on each traversal path in the expanded traversal path, and screening each traversal path based on the semantic information difference weight to obtain a target traversal path in the expanded traversal path; Traversing the advertising data along the target traversal path, determining the relationship edges between entities corresponding to nodes at each level in the advertising knowledge graph, and constructing an association relationship matrix between nodes at each level based on the relationship strength and semantic information of the relationship edges; For the advertising delivery data corresponding to the nodes at each level, based on the semantic information changes of the entities corresponding to the nodes at each level in the advertising delivery knowledge graph at different time points, determine the data change trend vector between the nodes at each level; Based on the fusion of the correlation matrix between nodes at each level and the data change trend vector, the hierarchical effect information of advertising delivery is obtained.

6. The artificial intelligence-based multi-platform advertising effect analysis method according to claim 1 is characterized in that: The method of performing advertising effect reasoning based on the relationship hierarchical matrix in combination with the hierarchical path and the relationship path in the advertising delivery knowledge graph to obtain potential effect information of the advertising delivery includes: If it is determined based on the relationship hierarchy matrix that the hierarchical path matches the relationship path, the hierarchical path and the relationship path are fused to obtain a fused path; For each path in the fused path, determining a delivery effect inference rule for the fused path based on the path characteristics of the path and the potential impact of each node in the path on the delivery effect; Based on the delivery effect inference rule, delivery effect inference is performed on the fusion path to obtain potential effect information of the advertisement delivery.

7. An artificial intelligence-based multi-platform advertising effect analysis system, characterized in that: The method for analyzing the effect of multi-platform advertising based on artificial intelligence according to any one of claims 1 to 6 is applied; the system for analyzing the effect of multi-platform advertising based on artificial intelligence comprises: A construction module is used to construct an advertising placement structure tree and an advertising placement knowledge graph; the advertising placement structure tree is constructed by taking a preset advertising campaign as a root node, different advertising placement platforms as child nodes under the root node, and advertising placement elements of different advertising placement platforms as different hierarchical nodes of its child nodes; the advertising placement knowledge graph is constructed by taking different advertising placement platforms and advertising placement subjects of different advertising placement platforms as entities, and taking the relationships between entities as edges; An effect trend analysis module is configured to start from the root node of the advertising placement structure tree, combine the semantic information of each node mapped to the advertising placement knowledge graph by the association mapping relationship, traverse the advertising placement data along different paths, analyze the association relationships and data change trends between nodes at each level, and obtain hierarchical effect information of advertising placement; the association mapping relationship represents the mapping relationship between the entities in the advertising placement knowledge graph and the nodes in the advertising placement structure tree; An effect inference module is used to perform advertising effect inference based on the relationship between entities in the advertising knowledge graph and the hierarchy of entities mapped to the advertising structure tree by combining the association mapping relationship to obtain potential effect information of the advertising; An effect decision analysis module, configured to perform delivery effect decision analysis based on the hierarchical effect information and the potential effect information, and obtain delivery optimization information for multi-platform advertising delivery; The specific process of determining the potential effect information of the advertisement placement includes: Determine the entity level of each entity in the advertising delivery knowledge graph in the advertising delivery structure tree based on the association mapping relationship; Based on the relationships between entities in the advertising knowledge graph and the entity hierarchy of each entity, a relationship hierarchy matrix is ​​constructed; the matrix elements in the relationship hierarchy matrix represent the association characteristics of the relationships between entities corresponding to the entity hierarchy in the advertising structure tree; In the advertising placement structure tree, traverse from the root node, and if the target node traversed in the advertising placement structure tree is a node corresponding to the mapping entity in the advertising placement knowledge graph, construct a hierarchical path based on the target node; Based on the relationship hierarchy matrix combined with the hierarchical path and the relationship path in the advertising delivery knowledge graph, the delivery effect is inferred to obtain potential effect information of the advertising delivery.

8. An electronic device comprising: Memory for storing computer software programs; A processor for reading and executing the computer software program, wherein when the processor executes the computer software program, it implements the multi-platform advertising delivery effect analysis method based on artificial intelligence as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium storing a computer software program, wherein: When the computer software program is executed by a processor, the multi-platform advertising delivery effect analysis method based on artificial intelligence as described in any one of claims 1 to 6 is implemented.

Images