Big data aggregation hidden danger discrimination method and system for association rules and agents

Abstract

The invention discloses a big data aggregation hidden danger judgment method and system of association rules and agents. The method comprises the following steps: preprocessing multi-source data of power equipment; for the preprocessed multi-source data of the power equipment, a frequent item set is obtained in a pruning and expansion processing mode; mining association rules of frequent item sets for the multi-source data of the power equipment, and determining common features and association rules of different data; and constructing an intelligent agent with understanding, memorizing and decision-making functions, deeply understanding the common features and association rules, performing reasoning analysis in combination with electric power rule knowledge, and performing man-machine interaction to obtain an analysis result of the aggregation hidden danger. According to the method, potential hidden dangers in association are analyzed, and finally man-machine interaction is performed to obtain the analysis result of the aggregation hidden dangers, so that the reliability and interpretability of the judgment of the aggregation hidden dangers are integrally improved.

Description

Background Art

[0003] Based on massive power operation and maintenance big data, association rules and intelligent agent technology are used to build intelligent operation and maintenance knowledge discovery, realize power equipment family disease analysis, improve the operating efficiency of power equipment, reduce downtime, discover potential safety hazards in advance and deal with abnormal situations in the power system, thereby improving the stability of the power system and ensuring stable and reliable power supply.

[0004] Emerging businesses such as power big data analysis, power system status analysis, and clustered family hidden danger analysis still face some technical challenges and limitations in practical applications. For example, the collection, storage, and processing of power big data require powerful computing and data processing capabilities, but the current computing resources and technical level are still difficult to meet these requirements. At the same time, power system status analysis and hidden danger investigation require real-time monitoring and analysis of a large amount of data, which puts higher requirements on the real-time monitoring and response capabilities of the power system.

[0005] Secondly, intelligent operation and maintenance knowledge discovery, power equipment family disease analysis and intelligent agent technology still face some challenges in data privacy and security in practical applications. For example, the leakage of power equipment data may pose a serious threat to the safety and stability of the power system, and how to protect the security and privacy of these sensitive data is still a problem that needs to be solved.

[0006] Finally, the construction of smart grids also needs to take into account the specific conditions and needs of different regions and different power systems in practical applications to achieve better adaptability and flexibility. For example, for power systems in remote and rural areas, simpler and more practical technologies and methods may be needed for construction and management.

[0007] In the existing identification of clustered hidden dangers, due to the use of simple rule-based judgments or data-driven methods, there is a problem that the basis for judgment is too simple, and the algorithm judgment process is a black box and lacks explainability, so it is difficult to meet actual application needs. Summary of the invention

[0008] The technical problem to be solved by the present invention is to provide a method and system for identifying clustered hidden dangers in big data based on association rules and intelligent agents in view of the deficiencies in the above-mentioned prior art, so as to solve the technical problem that it is difficult to identify clustered hidden dangers in actual power systems.

[0009] The present invention adopts the following technical solutions: The method for identifying hidden dangers of big data clustering based on association rules and intelligent agents includes the following steps: Preprocess multi-source data of power equipment; For the pre-processed multi-source data of power equipment, frequent itemsets are obtained through pruning and expansion processing; Conduct association rule mining of frequent item sets for multi-source data of power equipment to determine the common features and association rules of different data; Build an intelligent agent with understanding, memory, and decision-making capabilities, have a deep understanding of common features and association rules, perform reasoning and analysis based on knowledge of electricity rules, and conduct human-computer interaction to obtain analysis results of clustered hidden dangers.

[0010] Preferably, the multi-source data of the power equipment includes multi-value data, continuous monitoring data and text data of the power equipment; the multi-value data, continuous monitoring data and text data of the power equipment are processed by text data standardization, range standardization and numerical discretization.

[0011] Preferably, the ChiMerge algorithm is used to numerically discretize multi-source data of power equipment.

[0012] Preferably, for the pre-processed multi-source data of electric power equipment, frequent itemsets are obtained by pruning and expanding processing as follows: Divide the data into different blocks according to different manufacturers and store them in arrays to find frequent itemsets; Based on the improved Apriori algorithm, the correlation between each family defect index and the fault characteristic quantity is analyzed, and the equipment status reflected by each defect index is determined through the correlation relationship, and finally the corresponding association rules are obtained.

[0013] Preferably, the improved Apriori algorithm is specifically as follows: The candidate k-itemsets are given by The set of item sets is connected with itself; k-1 item sets are connected with themselves to generate k item sets. The premise of connecting k-1 item sets is that the previous k-2 item sets are exactly the same. If there are non-identical items, the non-identical items are deleted to obtain frequent item sets. The superset of the frequent itemset that contains the infrequent itemset is the infrequent itemset. When generating frequent itemsets, the superset containing the infrequent itemsets will be completely deleted.

[0014] Preferably, association rule mining is performed on multi-source data of power equipment to determine the common features and association rules of different data as follows: Through the first iteration of the Apriori algorithm, the multi-source data of the device is scanned, the frequency of each item is calculated, and a 1-candidate set is generated. , initialize k=1, set k=k+1; Use the iteratively discovered frequent (k-1)-item sets to generate new candidate k-item sets; the Apriori algorithm calculates the support of the candidate items each time it scans the data set to determine the candidate k-item sets ; Remove all candidate item sets whose support is less than the minimum support threshold; When no new frequent item sets are generated, the Apriori algorithm ends, and finally association rules are generated from frequent item sets.

[0015] Preferably, the agent reasoning analysis process is as follows: Through the semantic understanding and text splitting functions of the large model, combined with the reasoning analysis of the thinking chain, the intelligent agent decomposes the task of clustered hidden danger analysis into multiple subtasks such as associated feature mining, feature clustering sorting, and clustering identification. The intelligent agent makes a decision to continue the task or judge the task as completed and terminate the operation through reasoning and analysis of the execution task; Through the short-term memory and long-term memory mechanism, the execution process of the subtask is temporarily stored in the process of executing the clustered hidden danger mining task. At the same time, the external knowledge base is stored and retrieved through the vector database, and the knowledge base in the power field is combined to assist in the analysis of the clustered hidden danger defect problem; The intelligent agent interacts with the physical world through API and finally outputs the hidden danger analysis results.

[0016] In a second aspect, an embodiment of the present invention provides a big data clustering risk identification system based on association rules and intelligent agents, which is characterized by comprising: Data module, pre-processing multi-source data of power equipment; The processing module obtains frequent item sets through pruning and expansion processing for the pre-processed multi-source data of power equipment; The mining module mines association rules of frequent itemsets for multi-source data of power equipment to determine the common features and association rules of different data; The discrimination module builds an intelligent agent with understanding, memory, and decision-making capabilities, deeply understands common features and association rules, conducts reasoning analysis based on knowledge of power rules, and conducts human-computer interaction to obtain analysis results of clustered hidden dangers.

[0017] Preferably, the multi-source data of power equipment includes multi-value data, continuous monitoring data and text data of power equipment; the multi-value data, continuous monitoring data and text data of power equipment are processed by text data standardization, range standardization and numerical discretization, and the ChiMerge algorithm is used to numerically discretize the multi-source data of power equipment.

[0018] Preferably, for the pre-processed multi-source data of electric power equipment, frequent itemsets are obtained by pruning and expanding processing as follows: Divide the data into different blocks according to different manufacturers and store them in arrays to find frequent itemsets; Based on the improved Apriori algorithm, the correlation between each family defect index and the fault characteristic quantity is analyzed, and the equipment status reflected by each defect index is determined through the correlation relationship, and finally the corresponding association rules are obtained; the improved Apriori algorithm is specifically as follows: The candidate k-itemsets are given by The set of item sets is connected with itself; k-1 item sets are connected with themselves to generate k item sets. The premise of connecting k-1 item sets is that the previous k-2 item sets are exactly the same. If there are non-identical items, the non-identical items are deleted to obtain frequent item sets. The superset of the frequent itemset that contains the infrequent itemset is the infrequent itemset. When generating frequent itemsets, the superset containing the infrequent itemsets will be completely deleted.

[0019] Preferably, association rule mining is performed on multi-source data of power equipment to determine the common features and association rules of different data as follows: Through the first iteration of the Apriori algorithm, the multi-source data of the device is scanned, the frequency of each item is calculated, and a 1-candidate set is generated. , initialize k=1, set k=k+1; Use the iteratively discovered frequent (k-1)-item sets to generate new candidate k-item sets; the Apriori algorithm calculates the support of the candidate items each time it scans the data set to determine the candidate k-item sets ; Remove all candidate item sets whose support is less than the minimum support threshold; When no new frequent item sets are generated, the Apriori algorithm ends, and finally association rules are generated from frequent item sets.

[0020] Preferably, the agent reasoning analysis process is as follows: Through the semantic understanding and text splitting functions of the large model, combined with the reasoning analysis of the thinking chain, the intelligent agent decomposes the task of clustered hidden danger analysis into multiple subtasks such as associated feature mining, feature clustering sorting, and clustering identification. The intelligent agent makes a decision to continue the task or judge the task as completed and terminate the operation through reasoning and analysis of the execution task; Through the short-term memory and long-term memory mechanism, the execution process of the subtask is temporarily stored in the process of executing the clustered hidden danger mining task. At the same time, the external knowledge base is stored and retrieved through the vector database, and the knowledge base in the power field is combined to assist in the analysis of the clustered hidden danger defect problem; The intelligent agent interacts with the physical world through API and finally outputs the hidden danger analysis results.

[0021] In a third aspect, a computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for identifying the clustered hidden dangers of big data of the above-mentioned association rules and intelligent agents when executing the computer program.

[0022] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, including a computer program, which, when executed by a processor, implements the steps of the method for identifying the clustered hidden dangers of big data based on the above-mentioned association rules and intelligent agents.

[0023] In a fifth aspect, a chip comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for identifying the clustered hidden dangers of big data based on the above-mentioned association rules and intelligent agents when executing the computer program.

[0024] In a sixth aspect, an embodiment of the present invention provides an electronic device, including a computer program, which, when executed by the electronic device, implements the steps of the method for identifying the clustered hidden dangers of big data of the above-mentioned association rules and intelligent agents.

[0025] Compared with the prior art, the present invention has at least the following beneficial effects: A method for distinguishing clustered hidden dangers of big data based on association rules and intelligent agents includes multi-source data analysis of power equipment, association rule mining, intelligent agent construction, and clustered hidden danger mining model. The technical route proposed in the present invention is as follows: First, multi-valued data, continuous monitoring data, and text data of power equipment are processed, and the data is uniformly processed by text data standardization, range standardization, and numerical discretization. Secondly, frequent item sets are obtained through processing methods such as pruning and expansion to realize the analysis of structural similarities such as power system topology. Thirdly, association rule mining is performed for power equipment data to discover common features and association rules of different data. Finally, an intelligent agent with understanding, memory, and decision-making is constructed to deeply understand the association rules, combine the power rule knowledge stored in the memory module, perform reasoning analysis, and obtain the analysis results of clustered hidden dangers through human-computer interaction through the decision-making module.

[0026] Furthermore, the multi-source data setting is to improve the reliability of the analysis. Multiple data sources can provide enough feature information, so that there is enough basis for hidden danger analysis and the basis for judgment is more sufficient.

[0027] Furthermore, the main idea of ​​the ChiMerge algorithm is to sort all continuous data and divide them into multiple intervals, calculate the chi-square (chi) value of two adjacent intervals each time, and merge the two intervals with the smallest chi-square value each time. The idea of ​​the ChiMerge discretization method is derived from the chi-square test and is a bottom-up algorithm. A recursive method is used to find the best adjacent intervals to merge together until the conditions that meet the stop condition are found to merge into the largest interval. The basic idea of ​​ChiMerge: For accurate discretization, the relative class frequencies should be completely consistent within an interval. Therefore, if two adjacent intervals have very similar class distributions, the two intervals can be merged; otherwise, they should remain separate. A low chi-square value indicates that they have similar class distributions. The main benefits of the ChiMerge discretization method include the following aspects: Avoid overfitting and underfitting: The ChiMerge method can avoid overfitting the model on the training data by converting continuous variables into discrete variables, while performing well on new data and reducing the risk of underfitting. ‌Ensure that the discretized data has a certain statistical significance‌: The ChiMerge method relies on the chi-square test, and ensures that the discretized data has a certain statistical significance by merging adjacent values ​​until certain conditions are met. ‌Easy to iterate models and feature engineering‌: After discretizing continuous features, it becomes easier to add and reduce features, which helps to quickly iterate the model. In addition, the discretized features are more robust to abnormal data and can better handle outliers. ‌Introduce nonlinearity‌: After a single continuous feature is discretized into multiple ones, each variable has a separate weight, which is equivalent to introducing nonlinearity in the model and enhancing the model's fitting ability. In addition, the discretized features can be cross-featured to further introduce nonlinearity and improve the model's expressiveness.

[0028] Furthermore, pruning and expansion can screen key frequent item sets and improve the efficiency of discovering clustered hidden dangers.

[0029] Furthermore, the data is divided into several areas. The transactions in the database are divided into several non-overlapping blocks according to the defects in different areas; only one block is considered at a time, and all frequent items are generated for it. Then, the generated frequent item sets are non-destructively combined to create all possible frequent item sets. Based on the array frequent item set mining algorithm, all attribute values ​​are uniformly identified, and then the database is scanned, and all data related to the association analysis are saved in the defined two-dimensional array. In the process of frequent item set generation, only the two-dimensional array is scanned, and the database does not need to be scanned, thus avoiding the time of repeated database scanning.

[0030] Furthermore, association rule analysis can filter out frequent item sets and generate meaningful association rules to help conduct more accurate association mining; association rule analysis can help quickly identify clustering risks.

[0031] Furthermore, it improves the accuracy of reasoning: through a coherent reasoning method, the agent can constantly review and adjust its thinking during the reasoning process, and has the ability to self-correct, thus significantly improving the accuracy of reasoning. Adaptability and flexibility: the agent can constantly adjust its behavior patterns according to new data, adapt to the changing world, and perform well. Automated task execution: the agent can automatically perform complex tasks, improving efficiency and safety.

[0032] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0033] In summary, the present invention analyzes the potential risks in the association and finally obtains the analysis results of the clustered risks through human-computer interaction, thereby improving the reliability and explainability of the clustered risk identification as a whole.

[0034] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a schematic diagram of the process of the present invention; Figure 2 Schematic diagram of agent reasoning analysis; Figure 3 A thinking tree for identifying hidden dangers; Figure 4 A schematic diagram of a computer device provided by an embodiment of the present invention; Figure 5 The block diagram of a chip provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] In the description of the present invention, it should be understood that the terms “include” and “comprises” indicate the presence of described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0038] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an" and "the" are intended to include plural forms unless the context clearly indicates otherwise.

[0039] It should be further understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects are in an "or" relationship.

[0040] It should be understood that, although the terms first, second, third, etc. may be used to describe preset ranges, etc. in the embodiments of the present invention, these preset ranges should not be limited to these terms. These terms are only used to distinguish preset ranges from each other. For example, without departing from the scope of the embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0041] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0042] Various structural schematic diagrams of the embodiments disclosed in the present invention are shown in the accompanying drawings. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clear expression. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0043] Power big data analysis refers to the discovery of patterns and trends in a large amount of power data through mining and analysis, so as to provide decision support for the planning, operation and management of the power system. Power big data mainly includes equipment operation data, user power consumption data, environmental monitoring data, etc. By analyzing these data, predictive maintenance of power equipment can be achieved, potential safety hazards can be discovered in advance, and abnormal conditions in the power system can be handled. In addition, power big data analysis can also provide decision-making basis for the operation and management of the power market, thereby improving the operating efficiency and economic benefits of the power system.

[0044] Power system status analysis refers to the timely discovery of potential problems in the power system through real-time monitoring and analysis of various power system status parameters, and early warning and processing. Power system status analysis mainly includes equipment status monitoring, power grid flow analysis, voltage stability assessment, etc. Through real-time analysis of the power system status, the stability and reliability of the power system can be effectively improved, and the occurrence of faults and losses can be reduced.

[0045] Aggregate and family hidden danger analysis refers to the discovery of aggregate and family hidden dangers through inspection, analysis and management of power equipment, and taking targeted measures to deal with them. Aggregate hidden dangers refer to the fact that in the power system, certain equipment or areas are prone to become concentrated areas of failure due to their special location and structure. Family hidden dangers refer to the fact that certain equipment in the power system is prone to similar failures due to problems in its design, manufacturing or installation. Through the analysis of aggregate and family hidden dangers, the operating efficiency of power equipment can be effectively improved, downtime and maintenance costs can be reduced, and it also helps to improve the safety of the power system.

[0046] Based on massive power operation and maintenance big data, association rules and intelligent agent technology are used to build intelligent operation and maintenance knowledge discovery, realize power equipment family disease analysis, improve the operation efficiency of power equipment, reduce downtime, discover potential safety hazards in advance and deal with abnormal conditions in the power system, thereby improving the stability of the power system and ensuring stable and reliable power supply. Association rules are a mining method used to discover the relationship between items in a data set. They can effectively discover association rules in power equipment data and reveal the common characteristics and relationships between different equipment. Intelligent agent technology is a computational method that simulates human thinking and behavior, which can achieve in-depth understanding and reasoning analysis of association rules. By building an intelligent agent with understanding, memory, and decision-making capabilities, power equipment data can be analyzed and processed in an all-round way, thereby improving the operation efficiency and safety of the power system.

[0047] The present invention provides a method for distinguishing clustered hidden dangers of big data based on association rules and intelligent agents. The association relationship between each family defect index and the fault characteristic quantity is analyzed through the block array Apriori algorithm, and the equipment state reflected by each defect index is discovered through the association relationship. Finally, the corresponding association rules are obtained through the algorithm. The association rules of big data are analyzed through intelligent agent reasoning, and the task steps are disassembled through the thinking chain. The potential hidden dangers in the association are analyzed in combination with the knowledge rules of the power field of the memory module, and finally the analysis results of the clustered hidden dangers are obtained through human-computer interaction.

[0048] See also Figure 1 The present invention provides a method for distinguishing clustered hidden dangers of big data based on association rules and intelligent agents, which includes multi-source data analysis of power equipment, association rule mining, intelligent agent construction, and clustered hidden danger mining model. The specific steps are as follows: S1. Process multi-value data, continuous monitoring data and text data of power equipment, and process the data uniformly by using text data standardization, range standardization and numerical discretization; S101. Text data standardization The family defect data contains a lot of text data, such as manufacturer, equipment type, parts, raw materials, defective equipment, voltage level, etc. These will bring a lot of inconvenience when making association rules, such as reading problems, time efficiency problems, and accuracy problems. Therefore, for this type of problem, the corresponding category is used instead.

[0049] Table 1 Family defect indicators of power equipment

[0050] S102. Standardization by scope The defect data reflecting the power equipment contains a lot of data. This type of data is classified according to the level of the range, such as partial discharge. According to the "GB / T_7354-2003 Partial Discharge Measurement Standard", the partial discharge is within the normal range when it is less than or equal to 10PC, and it is judged as abnormal when it exceeds. The normal range of the mapped data within this range is 0, and the abnormal range is 1. In this way, these data are standardized according to some reference standards according to the normal or abnormal range.

[0051] S103, numerical discretization The ChiMerge algorithm is used to numerically discretize the data. The idea of ​​the ChiMerge discretization method is derived from the chi-square test and is a bottom-up algorithm. A recursive method is used to find the best adjacent intervals and merge them together until the conditions that meet the stop condition are found to merge into the largest interval. The basic idea of ​​ChiMerge: For accurate discretization, the relative class frequencies should be completely consistent within an interval. Therefore, if two adjacent intervals have very similar class distributions, the two intervals can be merged; otherwise, they should be kept separate. A low chi-square value indicates that they have similar class distributions.

[0052] S104, defect corresponding to fault characteristic quantity coding In the obtained transformer data, the defect manifestation is found through objective methods in order to prevent transformer failure. The corresponding transformer defect will cause the corresponding fault, so the corresponding fault type is quantified. The specific fault types are shown in Table 2 below.

[0053] Table 2 Fault type table

[0054] These characteristic quantities are of Boolean type, with 0 and 1 options, indicating whether a winding fault has occurred. If it has occurred, it is 1, and if it has not occurred, it is 0.

[0055] S2, obtain frequent item sets through pruning and expansion, and analyze the similarity of structures such as power system topology; Association rule mining is realized based on the improved Apriori algorithm. The specific steps are as follows: S201, array block division Before using the array-based Apriori algorithm, the data is divided into different blocks according to different manufacturers, and these blocks are stored in an array to find frequent item sets.

[0056] S202, array connection In the classic Apriori algorithm, in order to find , the candidate k-itemset is The set of item sets is connected with itself. The k-1 item set is connected with itself to generate the k item set. The premise of connecting the k-1 item set is that the previous k-2 item sets are exactly the same. If there are non-identical items, these non-identical items are deleted in this step to facilitate subsequent calculations.

[0057] S203, array pruning According to step S202, the supersets of the itemsets containing infrequent itemsets in the obtained itemsets are all infrequent itemsets. Thus, when generating frequent itemsets, all supersets containing infrequent itemsets are deleted to facilitate subsequent scanning to generate frequent itemsets.

[0058] S3. Perform association rule mining on power equipment data to discover common features and association rules of different data; Through the first iteration of the algorithm, the data is scanned, the frequency of each item is calculated, and a 1-candidate set is generated. , initialize k=1, set k=k+1; Use the iteratively discovered frequent (k-1)-item sets to generate new candidate k-item sets; each time the algorithm scans the data set, it needs to calculate the support of the candidate items to determine the candidate k-item sets ; Remove all candidate item sets whose support is less than the minimum support threshold; When no new frequent item sets are generated, the algorithm ends, and finally association rules are generated from frequent item sets.

[0059] S4. Construct an intelligent agent with understanding, memory, and decision-making capabilities, deeply understand the association rules, combine the power rules knowledge stored in the memory module, conduct reasoning analysis, and conduct human-computer interaction through the decision-making module to obtain the analysis results of the aggregated hidden dangers.

[0060] See also Figure 2 , the agent reasoning analysis process is as follows: S401, understanding module Through the semantic understanding and text splitting functions of the large model, combined with the reasoning analysis of the thinking chain, the intelligent agent can decompose the task of clustered hidden danger analysis into multiple subtasks such as associated feature mining, feature clustering sorting, and clustering identification, so as to effectively complete complex tasks. Furthermore, the intelligent agent can decide whether to continue to execute the task or judge the task as completed and terminate the operation through reasoning and analysis of the execution task.

[0061] See also Figure 3 , combined with the thinking chain, construct the logical chain in the analysis of clustered hidden dangers, form the form of a thinking tree, and assist in the analysis and identification of clustered hidden dangers.

[0062] S402, memory module Through the short-term memory and long-term memory mechanisms, the context of the task execution process is used to temporarily store the execution process of the subtask. At the same time, the external knowledge base is stored and retrieved through the vector database, and the knowledge base in the power field is combined to assist in the analysis of clustered hidden dangers and defects.

[0063] S403, decision module The intelligent agent is equipped with tool APIs, such as interactive interfaces, query tools, etc. Through these tool APIs, the intelligent agent interacts with the physical world and finally outputs the hidden danger analysis results to solve the actual problem of identifying concentrated hidden dangers in the power system.

[0064] Power big data analysis can discover the laws and trends in a large amount of power data through mining and analysis, and provide decision support for the planning, operation and management of the power system. By applying advanced data processing and analysis technologies, such as machine learning and data mining, it is possible to achieve predictive maintenance of power equipment, discover potential safety hazards in advance, and take appropriate measures to deal with abnormal situations in the power system.

[0065] Secondly, power system status analysis can timely detect potential problems in the power system, and conduct early warning and processing by real-time monitoring of various power system status parameters, such as voltage, current, frequency, etc. Through real-time analysis of the power system status, the stability and reliability of the power system can be effectively improved, and the occurrence of faults and losses can be reduced.

[0066] Finally, family hidden danger analysis can discover family hidden dangers through inspection, analysis and management of power equipment, and take targeted measures to deal with them. This will help improve the operating efficiency of power equipment, reduce downtime and maintenance costs, and also help improve the safety of the power system.

[0067] In short, by using association rules and intelligent agent technology to build an intelligent operation and maintenance knowledge discovery system, it will help to achieve all-round management and analysis of equipment and users in the power system, thereby improving the stability, reliability and safety of the power system. In the new stage of smart grid construction, the development of these emerging businesses will inject new impetus and vitality into the development of my country's power industry.

[0068] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as systems, methods or program products. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which may be collectively referred to herein as "circuits", "modules" or "platforms".

[0069] In another embodiment of the present invention, a system for distinguishing hidden dangers based on big data aggregation of association rules and intelligent agents is provided. The system can be used to implement the above-mentioned method for distinguishing hidden dangers based on big data aggregation of association rules and intelligent agents. Specifically, the system for distinguishing hidden dangers based on big data aggregation of association rules and intelligent agents includes a data module, a processing module, a mining module and a distinguishing module.

[0070] Among them, the data module pre-processes the multi-source data of power equipment; The multi-source data of power equipment include multi-value data, continuous monitoring data and text data of power equipment. The multi-value data, continuous monitoring data and text data of power equipment are processed by text data standardization, range standardization and numerical discretization. The ChiMerge algorithm is used to numerically discretize the multi-source data of power equipment.

[0071] The processing module obtains frequent item sets through pruning and expansion processing for the pre-processed multi-source data of power equipment; Divide the data into different blocks according to different manufacturers and store them in arrays to find frequent itemsets; Based on the improved Apriori algorithm, the correlation between each family defect index and the fault characteristic quantity is analyzed, and the equipment status reflected by each defect index is determined through the correlation relationship, and finally the corresponding association rules are obtained; the improved Apriori algorithm is specifically as follows: The candidate k-itemsets are given by The set of item sets is connected with itself; k-1 item sets are connected with themselves to generate k item sets. The premise of connecting k-1 item sets is that the previous k-2 item sets are exactly the same. If there are non-identical items, the non-identical items are deleted to obtain frequent item sets. The superset of the frequent itemset that contains the infrequent itemset is the infrequent itemset. When generating frequent itemsets, the superset containing the infrequent itemsets will be completely deleted.

[0072] The mining module mines association rules of frequent itemsets for multi-source data of power equipment to determine the common features and association rules of different data; Through the first iteration of the Apriori algorithm, the multi-source data of the device is scanned, the frequency of each item is calculated, and a 1-candidate set is generated. , initialize k=1, set k=k+1; Use the iteratively discovered frequent (k-1)-item sets to generate new candidate k-item sets; the Apriori algorithm calculates the support of the candidate items each time it scans the data set to determine the candidate k-item sets ; Remove all candidate item sets whose support is less than the minimum support threshold; When no new frequent item sets are generated, the Apriori algorithm ends, and finally association rules are generated from frequent item sets.

[0073] The discrimination module builds an intelligent agent with understanding, memory, and decision-making capabilities, deeply understands common features and association rules, conducts reasoning analysis based on knowledge of power rules, and conducts human-computer interaction to obtain analysis results of clustered hidden dangers.

[0074] Through the semantic understanding and text splitting functions of the large model, combined with the reasoning analysis of the thinking chain, the intelligent agent decomposes the task of clustered hidden danger analysis into multiple subtasks such as associated feature mining, feature clustering sorting, and clustering identification. The intelligent agent makes a decision to continue the task or judge the task as completed and terminate the operation through reasoning and analysis of the execution task; Through the short-term memory and long-term memory mechanism, the execution process of the subtask is temporarily stored in the process of executing the clustered hidden danger mining task. At the same time, the external knowledge base is stored and retrieved through the vector database, and the knowledge base in the power field is combined to assist in the analysis of the clustered hidden danger defect problem; The intelligent agent interacts with the physical world through API and finally outputs the hidden danger analysis results.

[0075] In another embodiment of the present invention, a terminal device is provided, which includes a processor and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, graphics processors (GPU), tensor processors (TPU), digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of the big data aggregation hidden danger identification method of association rules and intelligent agents, including: Preprocess the multi-source data of power equipment; obtain frequent item sets through pruning and expansion processing for the preprocessed multi-source data of power equipment; mine association rules of frequent item sets for multi-source data of power equipment to determine the common features and association rules of different data; build an intelligent agent with understanding, memory, and decision-making capabilities, deeply understand the common features and association rules, perform reasoning analysis based on knowledge of power rules, and conduct human-computer interaction to obtain analysis results of clustered hidden dangers.

[0076] See also Figure 4, the terminal device is a computer device. The computer device 60 of this embodiment includes: a processor 61, a memory 62, and a computer program 63 stored in the memory 62 and executable on the processor 61. When the computer program 63 is executed by the processor 61, the method for distinguishing hidden dangers of big data aggregation of association rules and intelligent agents in the embodiment is implemented. To avoid repetition, it is not described one by one here. Alternatively, when the computer program 63 is executed by the processor 61, the functions of each model / unit in the system for distinguishing hidden dangers of big data aggregation of association rules and intelligent agents in the embodiment are implemented. To avoid repetition, it is not described one by one here.

[0077] The computer device 60 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer device 60 may include, but is not limited to, a processor 61 and a memory 62. Those skilled in the art will appreciate that Figure 4 This is only an example of the computer device 60 and does not constitute a limitation of the computer device 60. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the computer device may also include input and output devices, network access devices, buses, etc.

[0078] The processor 61 may be a central processing unit (CPU), or other general-purpose processors, graphics processing units (GPU), tensor processing units (TPU), digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0079] The memory 62 may be an internal storage unit of the computer device 60, such as a hard disk or memory of the computer device 60. The memory 62 may also be an external storage device of the computer device 60, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the computer device 60.

[0080] Furthermore, the memory 62 may include both an internal storage unit of the computer device 60 and an external storage device. The memory 62 is used to store computer programs and other programs and data required by the computer device. The memory 62 may also be used to temporarily store data that has been output or is to be output.

[0081] See also Figure 5 The terminal device 600 is an electronic device, and the electronic device is in the form of a general computing device. The components of the electronic device may include but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0082] The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 performs the steps according to various exemplary embodiments of the present invention described in the above method section of this specification. For example, the processing unit 610 can perform the following steps: Figure 1 Follow the steps shown in .

[0083] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0084] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0085] Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0086] The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 650. Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, etc.

[0087] In another embodiment of the present invention, the present invention also provides a storage medium, specifically a computer-readable storage medium, which is a memory device in a terminal device for storing programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and the extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs. It should be noted that the computer-readable storage medium here can be a high-speed RAM memory, or a non-volatile memory (Non-VolatileMemory), such as at least one disk memory.

[0088] The processor may load and execute one or more instructions stored in a computer-readable storage medium to implement the corresponding steps of the method for distinguishing big data aggregation hazards related to association rules and intelligent agents in the above-mentioned embodiment; the processor may load and execute the following steps: Preprocess the multi-source data of power equipment; obtain frequent item sets through pruning and expansion processing for the preprocessed multi-source data of power equipment; mine association rules of frequent item sets for multi-source data of power equipment to determine the common features and association rules of different data; build an intelligent agent with understanding, memory, and decision-making capabilities, deeply understand the common features and association rules, perform reasoning analysis based on knowledge of power rules, and conduct human-computer interaction to obtain analysis results of clustered hidden dangers.

[0089] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention described and shown in the drawings here can usually be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0090] Simulation experiment A data set containing 1,000 samples was used for simulation experiments, including operation data, monitoring data and text description data of different types of power equipment. A unified data set was obtained by preprocessing and standardizing these data; then, the method of the present invention was used to perform frequent item set mining and association rule analysis.

[0091] The experimental results show that within the set threshold range, the method of the present invention can effectively discover the association rules in the power equipment data, and the mined rules have high confidence and support. In addition, through the deep understanding and reasoning analysis of the intelligent agent, multiple clustered hidden dangers were successfully identified, and accurate analysis results were obtained.

[0092] Application Examples An actual power system case was selected for analysis, which involved multiple substations and transmission lines with multiple hidden dangers and defects. A unified data set was obtained by preprocessing and standardizing the operation data, monitoring data and text description data of these devices. Then, the method of the present invention was used to perform frequent item set mining and association rule analysis.

[0093] After analysis, multiple association rules were found, which revealed the common characteristics and relationships between different power equipment. Through the deep understanding and reasoning analysis of the intelligent agent, multiple clustered hidden dangers were identified, such as the same hidden dangers in multiple transmission lines in a certain area, or similar defects in multiple equipment in a substation. These hidden dangers and defects may cause chain failures in the actual operation of the power system, leading to large-scale power outages. Through the analysis of the method of the present invention, these potential risks can be discovered in advance, and corresponding measures can be taken to deal with them, thereby improving the stability and reliability of the power system.

[0094] In summary, the present invention is a method and system for distinguishing clustered hidden dangers based on association rules and intelligent bodies in big data. The association relationship between each family defect index and the fault characteristic quantity is analyzed through the block array Apriori algorithm. The equipment status reflected by each defect index is discovered through the association relationship. Finally, the corresponding association rules are obtained through the algorithm. The task steps are disassembled through the thinking chain, and the potential hidden dangers in the association are analyzed in combination with the knowledge rules in the power field of the memory module. Finally, human-computer interaction is performed to obtain the analysis results of clustered hidden dangers. The reliability and explainability of the identification of clustered hidden dangers are improved as a whole.

[0095] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0096] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0097] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0098] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0099] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0100] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0101] If the integrated module / 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 this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0102] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices, and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0103] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0104] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0105] The above contents are only for explaining the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A method for identifying clustered hidden dangers in big data based on association rules and intelligent agents, characterized in that: The following steps are involved: Preprocess multi-source data of power equipment; For the pre-processed multi-source data of power equipment, frequent itemsets are obtained through pruning and expansion processing; Conduct association rule mining of frequent item sets for multi-source data of power equipment to determine the common features and association rules of different data; Build an intelligent agent with understanding, memory, and decision-making capabilities, have a deep understanding of common features and association rules, perform reasoning and analysis based on knowledge of electricity rules, and conduct human-computer interaction to obtain analysis results of clustered hidden dangers.

2. The method for distinguishing hidden dangers of big data aggregation based on association rules and intelligent agents according to claim 1 is characterized in that: The multi-source data of power equipment include multi-value data, continuous monitoring data and text data of power equipment; the multi-value data, continuous monitoring data and text data of power equipment are processed by text data standardization, range standardization and numerical discretization.

3. The method for identifying hidden dangers of big data aggregation based on association rules and intelligent agents according to claim 2 is characterized in that: The ChiMerge algorithm is used to numerically discretize multi-source data of power equipment.

4. The method for identifying hidden dangers of big data aggregation based on association rules and intelligent agents according to claim 1 is characterized in that: For the pre-processed multi-source data of power equipment, the frequent item sets are obtained through pruning and expansion processing as follows: Divide the data into different blocks according to different manufacturers and store them in arrays to find frequent itemsets; Based on the improved Apriori algorithm, the correlation between each family defect index and the fault characteristic quantity is analyzed, and the equipment status reflected by each defect index is determined through the correlation relationship, and finally the corresponding association rules are obtained.

5. The method for identifying hidden dangers of big data aggregation based on association rules and intelligent agents according to claim 4 is characterized in that: The improved Apriori algorithm is as follows: The candidate k-itemsets are given by The set of item sets is connected with itself; k-1 item sets are connected with themselves to generate k item sets. The premise of connecting k-1 item sets is that the previous k-2 item sets are exactly the same. If there are non-identical items, the non-identical items are deleted to obtain frequent item sets. The superset of the frequent itemset that contains the infrequent itemset is the infrequent itemset. When generating frequent itemsets, the superset containing the infrequent itemsets will be completely deleted.

6. The method for identifying hidden dangers of big data aggregation based on association rules and intelligent agents according to claim 1 is characterized in that: Association rules mining is performed on multi-source data of power equipment to determine the common characteristics and association rules of different data: Through the first iteration of the Apriori algorithm, the multi-source data of the device is scanned, the frequency of each item is calculated, and a 1-candidate set is generated. , initialize k=1, set k=k+1; Use the iteratively discovered frequent (k-1)-item sets to generate new candidate k-item sets; the Apriori algorithm calculates the support of the candidate items each time it scans the data set to determine the candidate k-item sets ; Remove all candidate item sets whose support is less than the minimum support threshold; When no new frequent item sets are generated, the Apriori algorithm ends, and finally association rules are generated from frequent item sets.

7. The method for identifying hidden dangers of big data aggregation based on association rules and intelligent agents according to claim 1 is characterized in that: The agent reasoning analysis process is as follows: Through the semantic understanding and text splitting functions of the large model, combined with the reasoning analysis of the thinking chain, the intelligent agent decomposes the task of clustered hidden danger analysis into multiple subtasks such as associated feature mining, feature clustering sorting, and clustering identification. The intelligent agent makes a decision to continue the task or judge the task as completed and terminate the operation through reasoning and analysis of the execution task; Through the short-term memory and long-term memory mechanism, the execution process of the subtask is temporarily stored in the process of executing the clustered hidden danger mining task. At the same time, the external knowledge base is stored and retrieved through the vector database, and the knowledge base in the power field is combined to assist in the analysis of the clustered hidden danger defect problem; The intelligent agent interacts with the physical world through API and finally outputs the hidden danger analysis results.

8. A big data clustering hidden danger identification system based on association rules and intelligent agents, characterized in that: include: Data module, pre-processing multi-source data of power equipment; The processing module obtains frequent item sets through pruning and expansion processing for the pre-processed multi-source data of power equipment; The mining module mines association rules of frequent itemsets for multi-source data of power equipment to determine the common features and association rules of different data; The discrimination module builds an intelligent agent with understanding, memory, and decision-making capabilities, deeply understands common features and association rules, conducts reasoning analysis based on knowledge of power rules, and conducts human-computer interaction to obtain analysis results of clustered hidden dangers.

9. The big data clustering hidden danger identification system based on association rules and intelligent agents according to claim 8 is characterized in that: The multi-source data of power equipment include multi-value data, continuous monitoring data and text data of power equipment. The multi-value data, continuous monitoring data and text data of power equipment are processed by text data standardization, range standardization and numerical discretization. The ChiMerge algorithm is used to numerically discretize the multi-source data of power equipment.

10. The big data clustering hidden danger identification system based on association rules and intelligent agents according to claim 8 is characterized in that: For the pre-processed multi-source data of power equipment, the frequent item sets are obtained through pruning and expansion processing as follows: Divide the data into different blocks according to different manufacturers and store them in arrays to find frequent itemsets; Based on the improved Apriori algorithm, the correlation between each family defect index and the fault characteristic quantity is analyzed, and the equipment status reflected by each defect index is determined through the correlation relationship, and finally the corresponding association rules are obtained; the improved Apriori algorithm is specifically as follows: The candidate k-itemsets are given by The set of item sets is connected with itself; k-1 item sets are connected with themselves to generate k item sets. The premise of connecting k-1 item sets is that the previous k-2 item sets are exactly the same. If there are non-identical items, the non-identical items are deleted to obtain frequent item sets. The superset of the frequent itemset that contains the infrequent itemset is the infrequent itemset. When generating frequent itemsets, the superset containing the infrequent itemsets will be completely deleted.

11. The big data clustering hidden danger identification system based on association rules and intelligent agents according to claim 8 is characterized in that: Association rules mining is performed on multi-source data of power equipment to determine the common characteristics and association rules of different data: Through the first iteration of the Apriori algorithm, the multi-source data of the device is scanned, the frequency of each item is calculated, and a 1-candidate set is generated. , initialize k=1, set k=k+1; Use the iteratively discovered frequent (k-1)-item sets to generate new candidate k-item sets; the Apriori algorithm calculates the support of the candidate items each time it scans the data set to determine the candidate k-item sets ; Remove all candidate item sets whose support is less than the minimum support threshold; When no new frequent item sets are generated, the Apriori algorithm ends, and finally association rules are generated from frequent item sets.

12. The big data clustering hidden danger identification system based on association rules and intelligent agents according to claim 8 is characterized in that: The agent reasoning analysis process is as follows: Through the semantic understanding and text splitting functions of the large model, combined with the reasoning analysis of the thinking chain, the intelligent agent decomposes the task of clustered hidden danger analysis into multiple subtasks such as associated feature mining, feature clustering sorting, and clustering identification. The intelligent agent makes a decision to continue the task or judge the task as completed and terminate the operation through reasoning and analysis of the execution task; Through the short-term memory and long-term memory mechanism, the execution process of the subtask is temporarily stored in the process of executing the clustered hidden danger mining task. At the same time, the external knowledge base is stored and retrieved through the vector database, and the knowledge base in the power field is combined to assist in the analysis of the clustered hidden danger defect problem; The intelligent agent interacts with the physical world through API and finally outputs the hidden danger analysis results.

13. A computer-readable storage medium storing one or more programs, characterized in that: The one or more programs include instructions, which, when executed by a computing device, cause the computing device to perform the method of any one of claims 1 to 7.

14. A computing device, characterized in that include: One or more processors, a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include steps for executing the method according to any one of claims 1 to 7.

Images