A processing method, system, device and medium for an automated rule configuration process

Abstract

The present invention relates to the technical field of data processing, and particularly to a processing method, system, device and medium for an automated rule configuration process. The method specifically includes: obtaining first placement rule data, performing semantic analysis and structured extraction on the first placement rule data to form second placement rule data; establishing a standard index library, constructing an index system for the second placement rule data according to the standard index library to generate a multi-fork tree rule; automatically verifying the multi-fork tree rule according to a rule verification tool to determine whether the multi-fork tree rule is reasonable, and if not, optimizing the multi-fork tree rule; obtaining historical placement advertisement data, and performing an advertisement placement scenario simulation test on the multi-fork tree rule according to the historical placement advertisement data. Through the generation, optimization and application of the multi-fork tree rule, the present invention realizes the intelligent configuration, management and optimization of advertisement placement rules.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a method, system, device and medium for processing an automated rule configuration process. Background Art

[0002] Today, with the increasingly fierce competition in the game industry, as a key tool to promote products to accurately reach users and increase market share, the effectiveness and flexibility of the game automated delivery system directly affect the success of game operation. However, the challenges faced by the current system in the aspect of rule configuration and management are becoming increasingly prominent, which not only limits the optimization potential of the system, but also increases the operation cost and risk, specifically manifested in the following aspects:

[0003] 1. Complexity of rule configuration and low efficiency: When different business teams or individuals configure delivery rules, there are significant differences in the naming and understanding of key indicators, which leads to frequent communication barriers and misunderstandings during the rule configuration process, greatly reducing the configuration efficiency. At the same time, the existing rule configuration process highly relies on manual work. From requirement sorting to rule writing, business personnel and technical personnel need to closely cooperate. However, the differences in their professional backgrounds often lead to poor information transmission, increasing the complexity and error rate of the configuration process.

[0004] 2. Heavy burden of technology transformation: Technical personnel need to manually transform the rules provided by business personnel in natural language or documents into code or configuration formats that the system can understand and execute. This process is both time-consuming and error-prone, seriously affecting the rapid response ability of the system. As the game scale expands and the delivery strategy becomes more complex, the number of rules that need to be converted increases sharply, further exacerbating the workload of the technical team.

[0005] 3. Cumbersome verification process: After the rule configuration is completed, multiple rounds of manual verification are required, including the correctness of business logic, system compatibility and potential conflicts, etc. This process takes a long time and is prone to missing problems.

[0006] 4. Lack of automated testing: The lack of effective automated verification tools makes it difficult to fully test and optimize the newly configured rules before going online, increasing the system instability and the uncertainty of the delivery effect.

[0007] 5. Limited system flexibility and scalability: The current rule configuration method often results in relatively fixed system rules, which are difficult to quickly adapt to market changes or business adjustments, limiting the innovation and flexibility of delivery strategies. With the enrichment of game features and the diversification of operation requirements, the system needs to be frequently functionally extended or refactored, but the limitations of the existing architecture in rule management make this process extremely difficult. Summary of the Invention

[0008] The object of the present invention is to provide a processing method, system, device and medium for an automated rule configuration process to solve at least one of the above-mentioned prior art problems.

[0009] In a first aspect, the present invention provides a processing method for an automated rule configuration process, which specifically includes:

[0010] Obtain first placement rule data, perform semantic analysis and structured extraction on the first placement rule data to form second placement rule data;

[0011] Establish a standard index library, and perform index system construction on the second placement rule data according to the standard index library to generate a multi-fork tree rule;

[0012] Automatically verify the multi-fork tree rule according to a rule verification tool to determine whether the multi-fork tree rule is reasonable, and if it is not reasonable, optimize the multi-fork tree rule;

[0013] Obtain historical placement advertisement data, and perform advertisement placement scenario simulation tests on the multi-fork tree rule according to the historical placement advertisement data;

[0014] Determine a placement advertisement plan for each placement advertisement according to the multi-fork tree rule, and perform display analysis on the placement advertisements that do not conform to the multi-fork tree rule.

[0015] In a second aspect, the present invention provides a processing system for an automated rule configuration process, which specifically includes:

[0016] A first processing module for obtaining first placement rule data, performing semantic analysis and structured extraction on the first placement rule data to form second placement rule data;

[0017] A second processing module for establishing a standard index library and performing index system construction on the second placement rule data according to the standard index library to generate a multi-fork tree rule;

[0018] A third processing module for automatically verifying the multi-fork tree rule according to a rule verification tool to determine whether the multi-fork tree rule is reasonable, and if it is not reasonable, optimizing the multi-fork tree rule;

[0019] A fourth processing module for obtaining historical placement advertisement data and performing advertisement placement scenario simulation tests on the multi-fork tree rule according to the historical placement advertisement data;

[0020] A fifth processing module for determining a placement advertisement plan for each placement advertisement according to the multi-fork tree rule and performing display analysis on the placement advertisements that do not conform to the multi-fork tree rule.

[0021] In a third aspect, the present invention provides a computer device, comprising: a memory, a processor, and a computer program stored on the memory. When the computer program is executed on the processor, it implements the processing method of the automated rule configuration process as described in any one of the above methods.

[0022] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it implements the processing method of the automated rule configuration process as described in any one of the above methods.

[0023] Compared with the prior art, the present invention has at least one of the following technical effects:

[0024] 1. Through the generation, optimization, and application of the multi-fork tree rules, the present invention realizes the intelligent configuration, management, and optimization of the advertising placement rules, improves the accuracy and effect of advertising placement, and provides more scientific and efficient placement decision-making support for advertisers.

[0025] 2. Through semantic analysis and structured extraction, the complex and fuzzy placement rule data is transformed into the second placement rule data with clear structure and easy to process, greatly improving the efficiency and accuracy of rule configuration.

[0026] 3. By establishing a standard index library, the standardization and normalization of the index system are realized, reducing the configuration errors caused by naming and understanding differences, and improving the maintainability and scalability of the system.

[0027] 4. An automated verification tool is introduced for automated verification to timely discover and optimize unreasonable rules, ensuring the rationality and effectiveness of the placement rules.

[0028] 5. Using the historical advertising placement data for scenario simulation tests and optimizing the placement strategy through machine learning algorithms, the accuracy and effect of advertising placement are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0030] Figure 1 is a flowchart of a processing method for an automated rule configuration process provided by an embodiment of the present invention;

[0031] Figure 2 is a structural diagram of a processing system for an automated rule configuration process provided by an embodiment of the present invention;

[0032] Figure 3 It is a schematic structural diagram of a computer device provided by an embodiment of the present invention. Detailed implementation manners

[0033] In the following description, specific details such as specific system architectures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0034] It should be understood that when used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0035] It should also be understood that the term "and / or" used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0036] As used in the specification of the present application and the appended claims, the term "if" can be interpreted as "when", "once", "in response to determining", or "in response to detecting" according to the context. Similarly, the phrase "if determined" or "if detected [the described condition or event]" can be interpreted as meaning "once determined", "in response to determining", "once detected [the described condition or event]", or "in response to detecting [the described condition or event]" according to the context.

[0037] In addition, in the description of the specification of the present application and the appended claims, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0038] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that specific features, structures, or characteristics described in connection with that embodiment are included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0039] In an embodiment of this application, the execution subject of the process includes a terminal device. The terminal device includes, but is not limited to, devices such as servers, computers, smart phones, and tablet computers that can execute the methods disclosed in this application. Figure 1 The flowchart of a processing method for an automated rule configuration process disclosed in the first embodiment of the present invention is shown as follows and will be described in detail:

[0040] S101, obtain first placement rule data, perform semantic analysis and structured extraction on the first placement rule data to form second placement rule data.

[0041] In this embodiment, in the game automated placement system, in order to formulate a new advertising placement strategy, business personnel use the XMind tool to create a placement rule file containing multiple levels and complex logical relationships. This file details the advertising display logic and priorities under different user groups, advertising channels, placement times, etc. In order to convert these complex placement rules into a format recognizable by the system, the system needs to perform semantic analysis and structured extraction on this XMind file.

[0042] Specifically, the business personnel upload XMind files through the system interface. After the system receives the files, it performs format verification to ensure the integrity and undamaged state of the files. It uses a dedicated XMind parsing library (such as the xmindparser library in Python) to read the content of the XMind files, parse them into JSON - formatted structured data, extract all the topics and sub - topics, as well as their hierarchical relationships and attribute information (such as titles, remarks, etc.). Natural Language Processing (NLP) is performed on the titles of each topic and sub - topic to identify the keywords and phrases therein, such as "user age", "advertising channel", "delivery time", etc. Using predefined thesaurus and rule libraries, the keywords are further parsed to determine their specific business meanings and constraints. In the structured data, the logical relationships (such as "and", "or" relationships), conditional judgments (such as "greater than", "less than", etc.) and execution actions (such as "display advertisement A", "adjust bid price", etc.) between the various rules are clearly represented. The structured data is stored in the system as the second delivery rule data for subsequent processing.

[0043] In this embodiment, by parsing the XMind file, the system can support business personnel to create complex delivery rules in a graphical way, reducing the threshold and difficulty of rule configuration. The semantic analysis process can automatically identify and parse the keywords and constraints in the delivery rules, reducing configuration errors caused by differences in human understanding. The second delivery rule data after structured extraction has a clear hierarchical structure and explicit logical relationships, facilitating technicians to understand and maintain. Generally speaking, the automated parsing and extraction process greatly shortens the time for rule configuration and improves work efficiency.

[0044] In some embodiments, in the above - mentioned step S101, the semantic analysis and structured extraction of the first delivery rule data to form the second delivery rule data specifically include:

[0045] Perform semantic analysis on the first delivery rule data using natural language processing technology to determine the key elements in the first delivery rule data, and obtain the third delivery rule data;

[0046] Extract the core semantic information of the third delivery rule data, construct a knowledge graph through the core semantic information, and use a graph embedding algorithm to perform vector representation on the knowledge graph to obtain a low - dimensional dense vector representation;

[0047] According to the low - dimensional dense vector representation, use a clustering algorithm to perform semantic similarity calculation and clustering analysis on the third delivery rule data to generate multiple rule clusters;

[0048] The association rule mining algorithm is used to identify the association relationships and dependency relationships among multiple rule clusters, and the second delivery rule data is formed according to the association relationships and the dependency relationships.

[0049] In this embodiment, the word segmentation algorithm in natural language processing technology is used to perform word segmentation on the first delivery rule data, obtain the keywords and phrases in the delivery rule data, and obtain the set of delivery rule keywords after word segmentation. Through the part-of-speech tagging algorithm, the set of delivery rule keywords after word segmentation is tagged with part-of-speech to determine the part-of-speech of each keyword, and the set of delivery rule keywords with part-of-speech tagging is obtained. According to the named entity recognition algorithm, the set of delivery rule keywords with part-of-speech tagging is used for named entity recognition to identify the key entities in the delivery rule data, such as brand names, product categories, etc., and the set of delivery rule key entities is obtained. The dependency parsing algorithm is used to perform syntactic analysis on the first delivery rule data, obtain the dependency relationships between the keywords in the delivery rule data, determine the semantic relationships between the keywords, and obtain the semantic dependency relationship graph between the delivery rule keywords. Through the semantic role labeling algorithm, the semantic dependency relationship graph between the delivery rule keywords is labeled with semantic roles to judge the semantic roles of each keyword in the delivery rule, such as conditions, target audiences, delivery times, etc., and the semantic dependency relationship graph of the delivery rule keywords with semantic role labeling is obtained. According to the knowledge base and ontology of the delivery rule business domain, the semantic dependency relationship graph of the delivery rule keywords with semantic role labeling is semantically extended and inferred to obtain the key elements and constraint conditions implicit in the delivery rule data, and the extended set of delivery rule key elements is obtained. The rule template of the delivery rule business domain is used to structurally represent the extended set of delivery rule key elements, obtain the structured third delivery rule data, determine the key elements of the delivery rule and their logical relationships, and form a structured representation of the delivery rule that can be executed by the delivery system.

[0050] According to the third delivery rule data, natural language processing technology is used to obtain the core semantic information of the delivery rule data through methods such as semantic analysis and keyword extraction, and obtain the key elements of the delivery rule and the relationships between them. According to the obtained core semantic information, knowledge graph construction technology is used to organize the key elements of the delivery rule into a structured knowledge graph by defining entities, attributes, and relationships, and obtain the knowledge graph model representing the semantics of the delivery rule. According to the constructed knowledge graph, the graph embedding algorithm is used to vectorize the entities and relationships in the knowledge graph, convert the high-dimensional sparse knowledge graph into a low-dimensional dense vector representation, and obtain the semantic vector representation of the delivery rule.

[0051] According to the low-dimensional dense vector representation, the K-means clustering algorithm is used to perform clustering analysis on the third delivery rule data. By calculating the Euclidean distance between vectors as the similarity metric, rule data with high similarity is divided into the same cluster, obtaining a preliminary result of rule cluster division. Obtain the preliminary rule clusters generated in the previous step. Use the silhouette coefficient evaluation method to calculate the average distance a between each rule data point and other points within the cluster and the minimum average distance b between this point and points in other clusters. The silhouette coefficient of each data point is obtained through the formula (b - a) / max(a, b). The value range of the silhouette coefficient is [-1, 1]. The closer it is to 1, the more appropriate the cluster the data point is assigned to. According to the silhouette coefficients calculated in the previous step, determine whether the current clustering result is reasonable. If there are many data points with low silhouette coefficients, it is considered that the current clustering effect is not good, and the clustering parameters such as the number of clusters K need to be adjusted and clustering is performed again until a better clustering result is obtained. By analyzing the clustering result, the central vector of each rule cluster is obtained. This vector can represent the average semantic feature of the cluster. Use the central vector of each rule cluster as the semantic representation of the cluster, forming multiple representative rule clusters. Use the average cosine similarity between the central vector of the rule cluster and each rule vector within the cluster to evaluate the internal consistency of each rule cluster. The higher the cosine similarity, the more similar the semantics of the rules within the cluster, thereby judging the clustering effect. For rule clusters with poor internal consistency, they can be further subdivided or merged, and finally rule clusters with high semantic similarity and good discrimination are obtained. By analyzing multiple rule clusters, determine the association and dependence relationships between the rule clusters, obtaining the association and dependence data between the rule clusters. According to the association and dependence data between the rule clusters, form the second delivery rule data and determine the final delivery strategy.

[0052] S102. Establish a standard index library, and perform index system construction on the second delivery rule data according to the standard index library to generate multi-way tree rules.

[0053] In this embodiment, in the game advertisement delivery system, in order to uniformly manage and optimize the advertisement delivery strategy, the system needs to establish a standard index library and perform index system construction on the second delivery rule data imported by business personnel according to this library, and finally generate multi-way tree rules. These multi-way tree rules will serve as the basis for advertisement delivery decisions and guide the precise delivery of advertisements.

[0054] Specifically, sort out all key indicators involved in the advertisement delivery business, such as user behavior indicators (click-through rate, conversion rate), advertisement channel indicators (CPC, CPM), delivery time indicators (time period, date), etc. Define and describe each indicator, clarify its calculation method and business meaning. Sort all indicators according to category, level, and importance to form a standard index library, and store the standard index library in the database for subsequent query and use.

[0055] Then, read the second delivery rule data, parse its structure and content, and extract the index items related to the standard index library. According to the classification and hierarchy of the standard index library, classify and organize the index items in the second delivery rule data. Use a decision tree algorithm or a similar method to construct a multi-level index system based on the logical and dependency relationships between the indexes. Each level of index represents a more specific delivery dimension or condition. During the construction process, ensure the integrity and consistency of the index system, and avoid redundancy and conflicts.

[0056] Based on the constructed index system, convert the second delivery rule data into a multi-way tree structure. Each node represents an index or a condition judgment, and the child nodes represent further subdivisions or execution actions under that condition. Use graph theory algorithms or specialized data structures to represent the multi-way tree rules, ensuring efficient traversal and querying. Name and annotate the multi-way tree rules so that business personnel and technical personnel can understand and maintain them.

[0057] In this embodiment, the establishment of the standard index library provides a unified basis and standard for the formulation and evaluation of advertising delivery strategies, improving the maintainability and scalability of the system. The systematic construction of the index system converts complex delivery rules into a clear multi-way tree structure, making the advertising delivery decision-making process more intuitive and efficient. The multi-way tree rules can comprehensively consider various delivery conditions and logical relationships, ensuring the accuracy and scientific nature of advertising delivery decisions. At the same time, since the multi-way tree rules are configurable, the system can flexibly respond to market changes and business requirements, and dynamically adjust and optimize the delivery strategy.

[0058] In some embodiments, in the above step S102, the systematic construction of the index system for the second delivery rule data according to the standard index library to generate multi-way tree rules specifically includes:

[0059] Use the analytic hierarchy process to classify and organize the second delivery rule data to obtain the dimension information and attribute information of the second delivery rule data;

[0060] According to the dimension information and attribute information, use a decision tree algorithm to construct a multi-level index system, and assign index weights to each level of index in the multi-level index system through the fuzzy comprehensive evaluation method;

[0061] According to the standard index library, standardize and correct the naming of each level of index in the multi-level index system to form multi-way tree rules.

[0062] In this embodiment, the second delivery rule data is classified and organized by using the hierarchical analysis method, and data with similar attributes are classified into the same category to form a plurality of data sets of different dimensions, thereby obtaining the dimension information of the second delivery rule data. By analyzing the characteristics of each dimensional data set, key information that can reflect the essential attributes of the dimensional data is extracted, and the attribute information of the second delivery rule data in different dimensions is obtained.

[0063] Obtain relevant dimension information and attribute information based on business scenarios, and determine the construction objectives and scope of the multi-level indicator system by analyzing business needs. Use the decision tree algorithm to process the acquired dimension information and attribute information, and construct a multi-level indicator system that meets business needs through recursive partitioning and feature selection, and obtain the hierarchical structure and logical relationship between indicators at all levels. Based on the constructed multi-level indicator system, use the fuzzy comprehensive evaluation method to assign weights to indicators at all levels, determine the importance of each indicator in the entire indicator system through expert scoring and weight calculation, and obtain the indicator weight distribution that reflects business attributes.

[0064] According to the standard indicator library, indicators at all levels in the multi-level indicator system are obtained to obtain a preliminary indicator naming list. By analyzing the business attributes, the specific business meaning of each indicator is determined, and the corresponding relationship between the business attributes and the indicators is obtained. According to the business attributes, the preliminary indicator naming list is corrected using standardized naming rules to obtain a standardized indicator naming list. By hierarchically dividing the standardized indicator naming list, the hierarchical relationship of indicators at all levels is determined to obtain the preliminary structure of the multi-level indicator system. According to the preliminary structure of the multi-level indicator system, a multi-tree structure is constructed for indicators at all levels to obtain an indicator system with a multi-tree structure. By verifying the business attributes of the indicator system with a multi-tree structure, the naming and structure of the final multi-level indicator system are determined to obtain a standardized multi-level indicator system, namely, a multi-tree rule.

[0065] S103, automatically verifying the multi-branch tree rule according to a rule verification tool to determine whether the multi-branch tree rule is reasonable, and optimizing the multi-branch tree rule if it is unreasonable.

[0066] In this embodiment, in the game advertisement delivery system, in order to ensure the accuracy and effectiveness of the multi-branch tree rules, the system introduces a rule verification tool. The tool can automatically verify the constructed multi-branch tree rules to check whether there are logical errors, data conflicts or problems that do not meet business specifications. Once unreasonableness is found, the system will automatically or prompt the user to optimize the multi-branch tree rules.

[0067] Specifically, design and implement a set of rule verification tools, which should include multiple verification modules to verify different aspects of the multi-way tree rules respectively. For example, the logic verification module checks whether the logical relationships and conditional judgments in the rules are correct; the data verification module checks whether the data used in the rules is valid and consistent; the business specification verification module checks whether the rules comply with the established business specifications and standards. Define detailed verification rules and verification algorithms for each verification module to ensure that all aspects of the multi-way tree rules can be comprehensively covered.

[0068] Then, input the constructed multi-way tree rules into the rule verification tool. The rule verification tool verifies the multi-way tree rules item by item according to the preset verification process and verification rules. For each verification item, the tool will output the verification result, including the identification of passing or failing the verification, as well as the specific reasons and locations for failing the verification. The system receives the verification results of the rule verification tool and analyzes and processes them. If all verification items pass, it indicates that the multi-way tree rules are reasonable, and the system can continue with subsequent placement operations. If there are verification failures, the system will prompt the user to optimize the multi-way tree rules according to the specific reasons and locations of the verification failures. The optimization may include modifying logical judgments, adjusting data inputs, correcting business specifications, etc. The user optimizes the multi-way tree rules according to the system's prompts. The optimized rules are input into the rule verification tool again for verification to ensure that the problems have been solved and the rules meet all verification requirements.

[0069] In this embodiment, through automated verification, errors and unreasonable parts in the multi-way tree rules can be discovered and corrected in a timely manner, thereby improving the quality and accuracy of the rules. Automated verification reduces the links of manual intervention and judgment, and reduces the risk of errors caused by human negligence or misunderstanding. Automated verification can quickly complete the verification of a large number of rules, saving the time and effort of manual verification and improving work efficiency.

[0070] In some embodiments, in the above step S103, the automated verification of the multi-way tree rules by the rule verification tool to determine whether the multi-way tree rules are reasonable, and if not, optimizing the multi-way tree rules specifically includes:

[0071] Traverse the multi-way tree rules using the depth-first search algorithm to obtain the attribute information and child node relationships of each node of the multi-way tree rules;

[0072] According to the attribute information and child node relationships of each node, judge whether the attribute values of each node meet the predefined constraint conditions, and whether the relationships between nodes meet the preset business logic requirements;

[0073] If the attribute values of each node do not conform to the predefined constraint conditions or the relationships between nodes do not meet the preset business logic requirements, a heuristic search algorithm is used to locally adjust the multi-way tree rule;

[0074] The analytic hierarchy process is used to evaluate the adjusted multi-way tree rule, and quantitative scoring is performed from multiple dimensions such as structural complexity, business coverage, and redundancy to obtain a quantitative scoring result. Whether to re-optimize the multi-way tree rule is determined according to the quantitative scoring result.

[0075] In this embodiment, according to the root node of the multi-way tree rule, the depth-first search algorithm is used to obtain the attribute information of the root node, including node type, node name, node value, etc., to obtain the complete attribute information of the root node. Based on the obtained root node information, it is judged whether the root node has child nodes. If there are child nodes, the number of child nodes is obtained to determine the number of child nodes of the root node. The depth-first search algorithm is used to obtain the attribute information of the first child node of the root node, including node type, node name, node value, etc., in the order from left to right, to obtain the complete attribute information of the first child node. According to the obtained attribute information of the first child node, it is judged whether this child node has child nodes. If so, the depth-first search algorithm is continued to obtain the attribute information of all child nodes of this child node until the leaf node is traversed, to obtain the attribute information of all nodes of the subtree with the first child node as the root. Backtracking to the root node, the same method is used to obtain the attribute information of the second child node of the root node and the attribute information of all its child nodes, to obtain the attribute information of all nodes of the subtree with the second child node as the root. And so on, the depth-first search algorithm is used to obtain the attribute information of all child nodes and their descendant nodes of the root node until the entire multi-way tree is traversed, to obtain the attribute information of all nodes in the multi-way tree. During the depth-first search process, by recording the parent node information of each node, the parent-child relationship between nodes is obtained, and the topological structure between nodes in the multi-way tree is determined. According to the obtained attribute information and parent-child relationship information of all nodes, the complete structure and node information of the multi-way tree rule are obtained, providing basic data for subsequent business logic processing.

[0076] According to the attribute information of each node, obtain the attribute value of the node. By comparing it with the predefined constraint conditions, judge whether the attribute value of the node meets the constraint conditions to obtain the legality result of the node attribute. Adopt the depth-first search algorithm to traverse the parent-child relationship between nodes, obtain the hierarchical structure and association relationship between nodes, and judge whether the relationship between nodes meets the business logic by matching the node relationship with the preset business logic requirements to obtain the compliance result of the node relationship. According to the legality result of the node attribute and the compliance result of the node relationship, use logical operations to comprehensively evaluate whether the attributes and relationships of the node simultaneously meet the predefined constraint conditions and business logic requirements to obtain the final verification result of the node.

[0077] According to the obtained list of nodes not meeting the requirements and the list of node relationships, adopt the heuristic search algorithm. By evaluating the impact of node attribute adjustment and node relationship adjustment on the satisfaction of business rules, obtain the optimal node attribute and relationship adjustment plan. According to the optimal node attribute and relationship adjustment plan, adopt the local adjustment algorithm of the tree. By modifying the attribute values of the nodes not meeting the requirements and adjusting the relationships between the nodes not meeting the requirements, obtain the adjusted multi-way tree rules. According to the adjusted multi-way tree rules, adopt the business rule verification algorithm. By verifying one by one whether each node attribute meets the constraint conditions and whether the relationships between nodes meet the business logic, judge whether the adjusted multi-way tree rules fully meet the business requirements. If the adjusted multi-way tree rules fully meet the business requirements, determine that the multi-way tree rules are the final business rules; if there are still node attributes or node relationships not meeting the requirements, return to continue local adjustment until the multi-way tree rules fully meeting the business requirements are obtained.

[0078] According to the adjusted multi-way tree rules, it is first necessary to evaluate its structural complexity. By analyzing the number of nodes, hierarchical depth, and number of branches of the multi-way tree, a preliminary quantitative score of the structural complexity is obtained. According to the preliminary quantitative score of the structural complexity, the analytic hierarchy process is used to further refine it. By constructing a judgment matrix, the weights of each node and level are obtained, and the final quantitative score of the structural complexity is obtained. According to the final quantitative score of the structural complexity, the business coverage rate is then evaluated. By analyzing the application of the multi-way tree rules in actual business scenarios, a preliminary quantitative score of the business coverage rate is obtained. According to the preliminary quantitative score of the business coverage rate, the analytic hierarchy process is used to further refine it. By constructing a judgment matrix, the weights of each business scenario are obtained, and the final quantitative score of the business coverage rate is obtained. According to the final quantitative score of the business coverage rate, the redundancy is then evaluated. By analyzing the repeated nodes and redundant paths in the multi-way tree rules, a preliminary quantitative score of the redundancy is obtained. According to the preliminary quantitative score of the redundancy, the analytic hierarchy process is used to further refine it. By constructing a judgment matrix, the weights of each redundant node and path are obtained, and the final quantitative score of the redundancy is obtained. According to the final quantitative scores of the structural complexity, business coverage rate, and redundancy, the analytic hierarchy process is used to conduct a comprehensive evaluation. By constructing a comprehensive judgment matrix, the comprehensive weights of each dimension are obtained, and the comprehensive quantitative score of the multi-way tree rules is obtained. According to the comprehensive quantitative score of the multi-way tree rules, it is judged whether it needs to be optimized again. If the comprehensive quantitative score is lower than the preset threshold, it is determined that the multi-way tree rules need to be optimized; otherwise, it is determined that the current multi-way tree rules do not need to be adjusted. Through the above steps, the final optimization decision is obtained to ensure that the multi-way tree rules reach the best state in multiple dimensions such as structural complexity, business coverage rate, and redundancy.

[0079] S104, obtain historical advertising delivery data, and perform an advertising delivery scenario simulation test on the multi-way tree rules according to the historical advertising delivery data.

[0080] In this embodiment, in the game advertising delivery system, in order to verify the effectiveness and applicability of the multi-way tree rules, the system needs to obtain historical advertising delivery data and perform an advertising delivery scenario simulation test on the multi-way tree rules based on these data. Through the simulation test, the performance of the rules in different scenarios can be evaluated, potential problems can be discovered and optimized.

[0081] Specifically, the system retrieves historical advertising data from the database, which should include key information such as the advertising release time, channels, target user groups, advertising content, release results (such as click-through rate, conversion rate, cost, etc.). Clean and preprocess the obtained data to remove invalid or abnormal data and ensure the accuracy and integrity of the data. Design an advertising release scenario simulation framework that can simulate different scenarios such as user behaviors, market environments, and release conditions. Use the multi-way tree rule as the decision engine of the simulation framework and simulate the advertising release process according to the logical relationships and conditional judgments in the rule. During the simulation process, use the historical advertising data as input to simulate the advertising display and click behaviors of different user groups at different times and through different channels.

[0082] Collect the data generated during the simulation test, including the simulated release results (such as simulated click-through rate, simulated conversion rate, etc.) and the actual release results (obtained from historical data). Evaluate the simulation results, compare the differences between the simulation results and the actual results, and analyze the reasons for the differences. Evaluate the performance of the multi-way tree rule in different scenarios, identify potential problems or deficiencies in the rule. Optimize the multi-way tree rule based on the results of the simulation test and the evaluation analysis, including adjusting logical judgments, modifying conditional parameters, adding or deleting rule nodes, etc. Retest the optimized rule to verify the optimization effect.

[0083] In this embodiment, through the simulation test, the effectiveness and applicability of the multi-way tree rule in different scenarios can be verified to ensure that the rule can accurately guide advertising release. Conducting a simulation test before actual release can timely detect and correct potential problems in the rule and reduce the release risks caused by rule errors. The results of the simulation test can provide data support for optimizing the release strategy and help the system more accurately locate the target user groups and release channels.

[0084] In some embodiments, in step S104 above, the advertising release scenario simulation test of the multi-way tree rule according to the historical advertising data specifically includes:

[0085] Perform an advertising release scenario simulation on the multi-way tree rule according to the historical advertising data, and at the same time use the Markov model to model the process of the advertising release scenario simulation to obtain the advertising release scenario simulation results;

[0086] According to the advertising release scenario simulation results, use the AdaBoost algorithm to train an ensemble decision tree classifier to obtain an optimized release strategy model.

[0087] In this embodiment, according to the historical advertising delivery data, a multi-way tree algorithm is used to model the advertising delivery scenario to obtain a multi-way tree model; according to the multi-way tree model, a Markov model is used to model the process of simulating the advertising delivery scenario to obtain a Markov state transition matrix; according to the Markov state transition matrix, a Monte Carlo simulation method is used to simulate and imitate the advertising delivery scenario to obtain an advertising delivery scenario simulation sequence; according to the advertising delivery scenario simulation sequence, a statistical analysis method is used to calculate the probability distribution of the occurrence of each advertising delivery scenario to obtain an advertising delivery scenario probability distribution result; according to the advertising delivery scenario probability distribution result, the delivery effect of each advertising delivery scenario is judged to obtain an advertising delivery scenario effect evaluation result.

[0088] According to the advertising delivery scenario simulation results, obtain the historical data of advertising delivery, including attributes such as advertising content, delivery time, delivery channel, target audience, etc. and effect indicators such as click-through rate and conversion rate of the advertisement, as the data set for training the AdaBoost model. Use data preprocessing techniques to clean, transform, and perform feature engineering on the obtained historical advertising delivery data, remove noise data, convert categorical variables into numerical variables, and select effect indicators such as click-through rate and conversion rate as classification labels to obtain a data set suitable for AdaBoost algorithm training. Divide the preprocessed advertising delivery data set into a training set and a test set through a cross-validation method. The training set is used to train the AdaBoost model, and the test set is used to evaluate the generalization performance of the model. Use the AdaBoost algorithm, set appropriate base classifiers (such as decision trees), and through multiple rounds of iterative training, in each round of iteration, adjust the training process of the base classifier according to the weights of the samples and update the sample weights to obtain a series of base classifiers, which are combined to form the final strong classifier, that is, the delivery strategy optimization model. According to the training process of the AdaBoost algorithm, by integrating the prediction results of multiple weak classifiers, obtain the predicted values of effect indicators such as click-through rate and conversion rate of the delivery strategy optimization model for the new advertising delivery scenario. Use the test set data to evaluate the trained delivery strategy optimization model, calculate evaluation indicators such as the accuracy, precision, recall rate, and F1 value of the model, and judge whether the performance of the model meets the requirements of advertising delivery optimization. According to the model evaluation results, optimize the delivery strategy optimization model, and improve the performance of the model by adjusting the hyperparameters of the AdaBoost algorithm (such as the number of iterations, learning rate, etc.), selecting more appropriate base classifiers, etc., to obtain the optimal delivery strategy optimization model. Apply the optimized delivery strategy optimization model to the actual advertising delivery scenario, and automatically adjust the advertising delivery strategy according to the prediction results of the model, such as delivery time, delivery channel, target audience, etc., to obtain higher advertising click-through rate and conversion rate, and achieve the optimization of advertising delivery.

[0089] S105. Determine the advertising placement plan for each advertising placement according to the multi - fork tree rule, and perform display analysis on the advertising placements that do not conform to the multi - fork tree rule.

[0090] In this embodiment, in the game advertising placement system, according to the multi - fork tree rule that has been constructed and verified, the system needs to determine a suitable advertising placement plan for each advertising to be placed. At the same time, the system also needs to identify and process those advertising placements that do not conform to the multi - fork tree rule for further analysis and optimization.

[0091] Specifically, the system traverses the multi - fork tree rule. According to the conditions and logical judgments of each node, it determines a matching advertising placement plan for each advertising to be placed. The advertising placement plan includes key information such as the advertising placement time, placement channels, target user groups, budget allocation, etc. When determining the advertising placement plan, the system needs to comprehensively consider factors such as the content of the advertisement, the attributes of the target users, and changes in the market environment.

[0092] During the process of determining the advertising placement plan, the system simultaneously checks whether each advertising to be placed meets all the conditions of the multi - fork tree rule. If it is found that an advertisement cannot find a matching placement path in the multi - fork tree rule or does not meet the conditions of a certain node, the system marks this advertisement as a non - compliant advertising placement. For non - compliant advertising placements, the system collects them for display analysis. The display analysis includes the basic information of the advertisement (such as advertisement ID, advertisement content, target user group, etc.), the specific reasons for non - compliance (such as lack of necessary attributes, mismatch between the target user group and the rule, etc.), and possible solutions (such as modifying the advertisement content, adjusting the target user group, etc.). The results of the display analysis can be used as a reference for advertising placement personnel for subsequent optimization processing.

[0093] In this embodiment, by automatically determining the advertising placement plan according to the multi - fork tree rule, the system can quickly allocate appropriate placement resources for each advertisement, improving the placement efficiency. Through a strict rule verification and placement plan determination process, the system can reduce placement errors caused by human judgment errors or negligence, reducing the error rate. Performing display analysis on non - compliant advertising placements helps advertising placement personnel promptly discover problems and deficiencies in the advertisements and conduct targeted optimizations to improve the quality of the advertisements.

[0094] In some embodiments, in step S105 above, the determining the advertising placement plan for each advertising placement according to the multi - fork tree rule specifically includes:

[0095] Construct an advertising placement decision tree model according to the multi - fork tree rule, and traverse the tree structure of the advertising placement decision tree model using a depth - first search algorithm to obtain multiple advertising placement plans;

[0096] For each advertising placement plan, calculate the comprehensive score of each advertising placement plan by setting multiple evaluation indicators;

[0097] Sort all advertising placement plans according to the comprehensive score, and determine several candidate advertising placement plans;

[0098] Use a multi-objective optimization algorithm to screen and optimize several candidate advertising placement plans, and determine the target advertising placement plan.

[0099] In this embodiment, a multi-way tree data structure is used to represent the advertising placement decision tree model. Each node of the tree represents a decision attribute or a placement plan, and the edges between the nodes represent decision conditions, obtaining a decision tree model structure that can meet the requirements of various placement scenarios. Using the depth-first search algorithm, starting from the root node of the decision tree, recursively traverse each node to obtain an advertising placement plan represented by the subtree rooted at the current node. During the traversal process, judge the walking direction according to the decision attributes and conditions of the node until reaching the leaf node, and obtain a complete advertising placement execution plan. By traversing all paths of the decision tree through depth-first search, multiple advertising placement plans covering various placement scenarios are obtained. Each plan contains a series of decision attributes and their corresponding values, representing the optimal placement execution strategy under specific audiences and placement requirements, and can guide the actual advertising placement process.

[0100] According to the attributes of the advertising placement plan such as the target audience, placement channel, placement time period, creative content, etc., use a multi-dimensional evaluation model to obtain the scores of each plan on each evaluation indicator. Through the method of weighted average, the scores of each evaluation indicator are weighted and summed to obtain the comprehensive score of each advertising placement plan. Among them, the weights of each indicator can be set and adjusted according to the needs of the advertiser and historical data. Sort all advertising placement plans according to the comprehensive score, and obtain several optimal plans with the highest scores as candidates.

[0101] By analyzing the business attributes of each advertising placement plan, the objective function in the multi-objective optimization algorithm is used to determine the initial fitness value of each plan. According to the business attributes such as the advertising placement budget, target audience, and placement time, constraint conditions are used to adjust the initial fitness value to obtain the adjusted fitness value. Based on the adjusted fitness value, a selection operation is adopted to obtain advertising placement plans with higher fitness values, and a set of initially screened advertising placement plans is obtained. According to the set of initially screened advertising placement plans, a crossover operation is adopted to obtain new advertising placement plans, and a set of advertising placement plans after crossover is obtained. Through the set of advertising placement plans after crossover, a mutation operation is adopted to obtain mutated advertising placement plans, and a set of mutated advertising placement plans is obtained. According to the set of mutated advertising placement plans, fitness evaluation is carried out to obtain the fitness value of each plan, and a set of advertising placement plans after evaluation is obtained. Through the set of advertising placement plans after evaluation, non-dominated sorting is adopted to obtain the non-dominated solution set, and the advertising placement plans in the non-dominated solution set are obtained. According to the advertising placement plans in the non-dominated solution set, crowding degree calculation is carried out to obtain the crowding degree value of each plan, and a set of advertising placement plans sorted by crowding degree is obtained. Through the set of advertising placement plans sorted by crowding degree, an elitist retention strategy is adopted to obtain the final advertising placement plan and determine the target advertising placement plan.

[0102] In some embodiments, in the above step S105, the displaying and analyzing the placed advertisements that do not conform to the multi-way tree rule specifically includes:

[0103] Obtain a number of placed advertisements that do not conform to the multi-way tree rule. For each placed advertisement, use the K-means clustering algorithm for grouping, and perform feature statistics on the placed advertisements in each group, calculate the support and confidence between different advertisement feature combinations, and obtain the first analysis result;

[0104] Use the association rule mining algorithm to analyze the association relationship between a number of placed advertisements that do not conform to the multi-way tree rule and a number of placed advertisements that conform to the multi-way tree rule, and obtain the second analysis result;

[0105] Optimize and improve the multi-way tree rule according to the first analysis result and the second analysis result.

[0106] In this embodiment, an initial data set of these advertisements is obtained according to a number of delivered advertisements that do not conform to the multi - tree rule. By using the K - means clustering algorithm to group the initial data set, the group to which each advertisement belongs is determined. According to the delivered advertisements of each group, the feature data of these advertisements are obtained, and the feature statistical results of each group are obtained. By analyzing the feature statistical results of each group, the support and confidence between different advertisement feature combinations are determined. According to the calculated support and confidence, a first analysis result is obtained, and the association rule of the advertisement feature combination is obtained.

[0107] According to the attribute information of the delivered advertisements, the multi - tree rule is used to classify the advertisements, and the advertisement set A that conforms to the multi - tree rule and the advertisement set B that does not conform to the multi - tree rule are obtained. By scanning the advertisements in the advertisement sets A and B, various attribute combinations of the advertisements are obtained, and the set of advertisement attribute combinations is obtained. According to the set of advertisement attribute combinations, the Apriori algorithm is used to generate frequent item sets, and the frequent combination patterns of advertisement attributes are obtained. By calculating the support and confidence of the frequent item sets, the association rules that meet the minimum support and minimum confidence thresholds are obtained, and the association relationship between advertisement attributes is obtained. According to the association rules of advertisement attributes, the correlation between the advertisements that do not conform to the multi - tree rule and the advertisements that conform to the multi - tree rule is judged, and a second analysis result is obtained, and the association pattern between advertisements is obtained.

[0108] Based on the first analysis result, it is determined which advertisement feature combinations have high support and confidence in the delivered advertisements, and the specific features of these combinations are obtained. According to these specific features, the advertisement feature combinations that do not conform to the multi - tree rule are obtained, and the performance of these combinations in advertisement delivery is determined. By further analyzing the performance of these advertisement feature combinations, their distribution in different groups is determined, and the feature distribution results of each group are obtained. According to the feature distribution results of each group, the advertisement feature combinations of different groups are obtained, and the support and confidence of these combinations in each group are determined. By comparing the support and confidence of each group, it is determined which groups of advertisement feature combinations have high relevance, and the specific features of these groups are obtained. According to these specific features, the performance of the advertisement feature combinations that do not conform to the multi - tree rule in different groups is obtained, and their effects in advertisement delivery are determined. By analyzing these effects, it is determined which advertisement feature combinations have high delivery effects in different groups, and the specific performance of these combinations is obtained. According to these specific performances, the delivery effects of the advertisement feature combinations that do not conform to the multi - tree rule in different groups are obtained, and their actual performances in advertisement delivery are determined. By summarizing these actual performances, it is determined which advertisement feature combinations have high delivery effects in different groups.

[0109] Based on the second analysis result, the advertisements that do not conform to the multi - fork tree rule are analyzed in an associated mode to obtain the advertisements that conform to the multi - fork tree rule related to them, and an optimized advertisement recommendation set for placement is obtained. By analyzing the attribute distribution and placement effect of the advertisement recommendation set, an optimized placement strategy is obtained, and a method for improving the accuracy and conversion rate of advertisement placement is determined.

[0110] Referring to Figure 2 , an embodiment of the present invention provides a processing system 2 for an automated rule configuration process. The system 2 specifically includes:

[0111] A first processing module 201, configured to obtain first placement rule data, perform semantic analysis and structured extraction on the first placement rule data, and form second placement rule data;

[0112] A second processing module 202, configured to establish a standard index library, and perform index system construction on the second placement rule data according to the standard index library to generate a multi - fork tree rule;

[0113] A third processing module 203, configured to perform automated verification on the multi - fork tree rule according to a rule verification tool, determine whether the multi - fork tree rule is reasonable, and if not, optimize the multi - fork tree rule;

[0114] A fourth processing module 204, configured to obtain historical placement advertisement data, and perform advertisement placement scenario simulation tests on the multi - fork tree rule according to the historical placement advertisement data;

[0115] A fifth processing module 205, configured to determine a placement advertisement plan for each placement advertisement according to the multi - fork tree rule, and perform display analysis on the placement advertisements that do not conform to the multi - fork tree rule.

[0116] It can be understood that the content in the embodiment of the processing method of the automated rule configuration process as Figure 1 shown is applicable to the embodiment of the processing system of the automated rule configuration process. The functions specifically implemented by the embodiment of the processing system of the automated rule configuration process are the same as those in the embodiment of the processing method of the automated rule configuration process as Figure 1 shown, and the beneficial effects achieved are also the same as those in the embodiment of the processing method of the automated rule configuration process as Figure 1 shown.

[0117] It should be noted that for the information interaction, execution process, etc. between the above - mentioned systems, since they are based on the same concept as the method embodiment of the present invention, their specific functions and the technical effects brought can be specifically referred to the method embodiment part, and will not be elaborated here.

[0118] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In practical applications, the above functions can be allocated to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiment and will not be elaborated here.

[0119] Referring to Figure 2 , an embodiment of the present invention further provides a computer device 3, including: a memory 302, a processor 301, and a computer program 303 stored on the memory 302. When the computer program 303 is executed on the processor 301, it implements the processing method of the automated rule configuration process described in any one of the above methods.

[0120] The computer device 3 may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art can understand that Figure 2 This is only an example of the computer device 3 and does not constitute a limitation on the computer device 3. It may include more or fewer components than shown in the figure, or combine some components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0121] The so-called processor 301 may be a central processing unit (CPU), and the processor 301 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0122] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as the hard disk or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk equipped on the computer device 3, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 302 may also include both the internal storage unit and the external storage device of the computer device 3. The memory 302 is used to store an operating system, application programs, a Boot Loader, data, and other programs, such as the program code of the computer program. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0123] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it implements the processing method of the automated rule configuration process described in any one of the above methods.

[0124] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above embodiment methods of the present application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the above various method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, an executable file, or some intermediate form, etc. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the photographing device / terminal device, a recording medium, a computer memory, a Read-Only Memory (ROM), a Random Access Memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium may not be an electrical carrier signal and a telecommunication signal.

[0125] In the above embodiments, the descriptions of the various embodiments have their own focuses. For parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0126] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0127] In the embodiments disclosed in this application, it should be understood that the disclosed devices / terminal devices and methods can be implemented in other ways. For example, the device / terminal device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of the devices or units can be in an electrical, mechanical or other form.

[0128] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

Claims

1. A processing method for an automated rule configuration process, characterized in that The method specifically includes: Obtain the first delivery rule data, perform semantic analysis and structured extraction on the first delivery rule data to form the second delivery rule data; Establish a standard index library, and construct an index system for the second delivery rule data according to the standard index library to generate a multi - fork tree rule; Automatically verify the multi - fork tree rule according to a rule verification tool to determine whether the multi - fork tree rule is reasonable. If it is not reasonable, optimize the multi - fork tree rule; Obtain historical advertising delivery data, and perform an advertising delivery scenario simulation test on the multi - fork tree rule according to the historical advertising delivery data; Among them, the performing an advertising delivery scenario simulation test on the multi - fork tree rule according to the historical advertising delivery data specifically includes: Perform an advertising delivery scenario simulation on the multi - fork tree rule according to the historical advertising delivery data, and at the same time use a Markov model to model the process of the advertising delivery scenario simulation to obtain an advertising delivery scenario simulation result; According to the advertising delivery scenario simulation result, use the AdaBoost algorithm to train an ensemble decision tree classifier to obtain a delivery strategy optimization model; Among them, the performing an advertising delivery scenario simulation on the multi - fork tree rule according to the historical advertising delivery data, and at the same time using a Markov model to model the process of the advertising delivery scenario simulation to obtain an advertising delivery scenario simulation result specifically includes: According to the historical advertising delivery data, use a multi - fork tree algorithm to model the advertising delivery scenario to obtain a multi - fork tree model; according to the multi - fork tree model, use a Markov model to model the process of the advertising delivery scenario simulation to obtain a Markov state transition matrix; according to the Markov state transition matrix, use the Monte Carlo simulation method to simulate and simulate the advertising delivery scenario to obtain an advertising delivery scenario simulation sequence; according to the advertising delivery scenario simulation sequence, use a statistical analysis method to calculate the probability distribution of the occurrence of each advertising delivery scenario to obtain an advertising delivery scenario probability distribution result; according to the advertising delivery scenario probability distribution result, judge the delivery effect of each advertising delivery scenario to obtain an advertising delivery scenario effect evaluation result; Determine the advertising delivery plan for each delivered advertisement according to the multi - fork tree rule, and display and analyze the delivered advertisements that do not conform to the multi - fork tree rule.

2. The method according to claim 1, wherein The performing semantic analysis and structured extraction on the first delivery rule data to form the second delivery rule data specifically includes: Use natural language processing technology to perform semantic analysis on the first delivery rule data to determine the key elements in the first delivery rule data to obtain the third delivery rule data; Extract the core semantic information of the third delivery rule data, construct a knowledge graph through the core semantic information, and use a graph embedding algorithm to perform vector representation on the knowledge graph to obtain a low - dimensional dense vector representation; According to the low - dimensional dense vector representation, use a clustering algorithm to perform semantic similarity calculation and clustering analysis on the third delivery rule data to generate multiple rule clusters; The association rule mining algorithm is used to identify the association relationships and dependency relationships among multiple rule clusters, and the second placement rule data is formed according to the association relationships and the dependency relationships.

3. The method according to claim 2, wherein The index system construction of the second placement rule data is carried out according to the standard index library to generate a multi-way tree rule, which specifically includes: The analytic hierarchy process is used to classify and organize the second placement rule data to obtain the dimension information and attribute information of the second placement rule data; According to the dimension information and attribute information, a multi-level index system is constructed by using the decision tree algorithm, and index weights are assigned to the indexes at all levels of the multi-level index system by using the fuzzy comprehensive evaluation method; According to the standard index library, the naming of the indexes at all levels in the multi-level index system is corrected and standardized to form a multi-way tree rule.

4. The method according to claim 1, characterized in that, The multi-way tree rule is automatically verified by using a rule verification tool to determine whether the multi-way tree rule is reasonable. If it is not reasonable, the multi-way tree rule is optimized, which specifically includes: The depth-first search algorithm is used to traverse the multi-way tree rule to obtain the attribute information and child node relationships of each node of the multi-way tree rule; According to the attribute information and child node relationships of each node, it is judged whether the attribute values of each node meet the predefined constraint conditions and whether the relationships between nodes meet the preset business logic requirements; If the attribute values of each node do not meet the predefined constraint conditions or the relationships between nodes do not meet the preset business logic requirements, the heuristic search algorithm is used to perform local adjustment on the multi-way tree rule; The analytic hierarchy process is used to evaluate the adjusted multi-way tree rule, and quantitative scoring is performed from multiple dimensions such as structural complexity, business coverage rate, and redundancy to obtain a quantitative scoring result. According to the quantitative scoring result, it is determined whether to optimize the multi-way tree rule again.

5. The method according to claim 1, characterized in that The placement advertisement plan for each placement advertisement is determined according to the multi-way tree rule, which specifically includes: An advertisement placement decision tree model is constructed according to the multi-way tree rule, and the depth-first search algorithm is used to traverse the tree structure of the advertisement placement decision tree model to obtain multiple advertisement placement plans; For each advertisement placement plan, the comprehensive score of each advertisement placement plan is calculated by setting multiple evaluation indexes; All advertisement placement plans are sorted according to the comprehensive score to determine several candidate advertisement placement plans; The multi-objective optimization algorithm is used to screen and optimize several candidate advertisement placement plans to determine the target advertisement placement plan.

6. The method according to claim 5, wherein The display analysis of the placement advertisements that do not conform to the multi-way tree rule is carried out, which specifically includes: Several placement advertisements that do not conform to the multi-way tree rule are obtained. For each placement advertisement, the K-means clustering algorithm is used for grouping, and the characteristics of the placement advertisements in each group are statistically analyzed, and the support degree and confidence degree between different advertisement feature combinations are calculated to obtain the first analysis result; The association rule mining algorithm is used to analyze the association relationships between several placement advertisements that do not conform to the multi-way tree rule and several placement advertisements that conform to the multi-way tree rule to obtain the second analysis result; Optimize and improve the multi - fork tree rule according to the first analysis result and the second analysis result.

7. A processing system for an automated rule configuration process, characterized in that, The system specifically includes: A first processing module, configured to obtain first placement rule data, perform semantic analysis and structured extraction on the first placement rule data, and form second placement rule data; A second processing module, configured to establish a standard index library, and construct an index system for the second placement rule data according to the standard index library to generate a multi - fork tree rule; A third processing module, configured to automatically verify the multi - fork tree rule according to a rule verification tool, determine whether the multi - fork tree rule is reasonable, and if not, optimize the multi - fork tree rule; A fourth processing module, configured to obtain historical advertising placement data, and perform an advertising placement scenario simulation test on the multi - fork tree rule according to the historical advertising placement data; Among them, the performing an advertising placement scenario simulation test on the multi - fork tree rule according to the historical advertising placement data specifically includes: Performing an advertising placement scenario simulation on the multi - fork tree rule according to the historical advertising placement data, and simultaneously using a Markov model to model the process of the advertising placement scenario simulation to obtain an advertising placement scenario simulation result; According to the advertising placement scenario simulation result, using the AdaBoost algorithm to train an ensemble decision tree classifier to obtain a placement strategy optimization model; Among them, the performing an advertising placement scenario simulation on the multi - fork tree rule according to the historical advertising placement data, and simultaneously using a Markov model to model the process of the advertising placement scenario simulation to obtain an advertising placement scenario simulation result specifically includes: According to the historical advertising placement data, using a multi - fork tree algorithm to model the advertising placement scenario to obtain a multi - fork tree model; according to the multi - fork tree model, using a Markov model to model the process of the advertising placement scenario simulation to obtain a Markov state transition matrix; according to the Markov state transition matrix, using the Monte Carlo simulation method to simulate and simulate the advertising placement scenario to obtain an advertising placement scenario simulation sequence; according to the advertising placement scenario simulation sequence, using a statistical analysis method to calculate the probability distribution of the occurrence of each advertising placement scenario to obtain an advertising placement scenario probability distribution result; according to the advertising placement scenario probability distribution result, judging the placement effect of each advertising placement scenario to obtain an advertising placement scenario effect evaluation result; A fifth processing module, configured to determine an advertising placement plan for each placed advertisement according to the multi - fork tree rule, and display and analyze the placed advertisements that do not conform to the multi - fork tree rule.

8. A computer device, characterized in that, Including: A memory, a processor, and a computer program stored on the memory. When the computer program is executed on the processor, it implements the processing method of the automated rule configuration process as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, A computer program is stored thereon. When the computer program is run by the processor, it implements the processing method of the automated rule configuration process as described in any one of claims 1 to 6.

Images