Fuel data intelligent management method and system based on data center

Abstract

The invention provides a fuel data intelligent management method and system based on a data center, and relates to the technical field of production data management, and the method comprises the steps: decomposing a fuel management period and analyzing a management target, and obtaining a data factor of the management target; establishing a data acquisition path according to the data factors; acquiring real-time update data through a data acquisition path, positioning a fuel management period, and constructing a management period data block; performing management cycle characteristic analysis according to the management cycle data blocks to obtain cycle fuel characteristics; and full-period supply unbalance analysis is carried out according to the periodic fuel characteristics, unbalance nodes and unbalance characteristics are obtained for balance compensation, and a full-period balance management strategy is obtained. The technical problem that accurate data support cannot be provided for fuel supply decision analysis due to the fact that a traditional management method is tedious in processing flow and lacks systematic analysis means for the whole cycle is solved, the fuel data processing efficiency and accuracy are improved, and the stability and continuity of fuel whole-cycle supply are enhanced.

Description

Technical Field

[0001] The present application relates to the technical field of production data management, and specifically to a method and system for intelligent management of fuel data based on a data middle platform. Background Art

[0002] The fuel supply of thermal power generation requires accurate data support in every link, from procurement, transportation to storage and consumption. The accuracy of fuel data management directly affects the stability of fuel supply and the efficiency of energy production. Existing fuel data management methods often have cumbersome processes in data collection, cleaning and processing. Managers need to manually collect various types of data and filter and process the data through traditional algorithms. The lack of clear goal orientation leads to redundant collected data and partial disconnection from actual management needs. In addition, traditional methods usually only analyze data for a single management link, such as simple statistics of coal procurement volume, inventory, consumption and other data, and lack a comprehensive analysis of the correlation between various links in the entire supply cycle. Therefore, this data management method is difficult to effectively monitor and predict the entire fuel supply chain throughout the entire cycle, and cannot timely detect potential supply imbalances or abnormal situations, resulting in the inability to provide accurate data support for decision-making analysis of fuel supply, which in turn affects the stability and sustainability of fuel supply. Summary of the invention

[0003] The present application provides a fuel data intelligent management method and system based on a data middle platform, which solves the technical problems of the traditional fuel data management method, which has a cumbersome data processing process and lacks systematic analysis methods for the fuel management cycle, resulting in the inability to provide accurate data support for fuel supply decision analysis. It achieves the technical effect of improving the efficiency and accuracy of fuel data processing, thereby enhancing the stability and sustainability of the fuel supply throughout the entire cycle.

[0004] In view of the above problems, on the one hand, the present application provides a fuel data intelligent management method based on a data middle platform, the method comprising: decomposing the fuel management cycle, parsing the management objectives of the fuel management cycle, and obtaining the data factors of the management objectives; establishing a data acquisition path according to the data factors, the data acquisition path is mapped and associated with the data factors, and the data acquisition path uses the data factors as data acquisition indexes, and the data acquisition path is used to establish a connection between the data middle platform and the data source platform; obtaining real-time updated data of the data source platform through the data acquisition path, locating the fuel management cycle according to the data factors, and constructing a management cycle data block and storing it in the data middle platform; performing feature analysis of the management cycle according to the management cycle data block to obtain cycle fuel characteristics; based on the supply balance influence relationship of the fuel management cycle, performing full-cycle supply imbalance analysis according to the cycle fuel characteristics to obtain imbalance nodes and imbalance characteristics; performing balance compensation according to the imbalance nodes and imbalance characteristics to obtain a full-cycle balance management strategy.

[0005] On the other hand, the present application also provides a fuel data intelligent management system based on a data middle platform, the system comprising: a management target parsing module, used to decompose the fuel management cycle, parse the management target of the fuel management cycle, and obtain the data factor of the management target; a data acquisition path establishment module, used to establish a data acquisition path according to the data factor, the data acquisition path is associated with the data factor mapping, and the data acquisition path uses the data factor as the data acquisition index, and the data acquisition path is used to establish a connection between the data middle platform and the data source platform; a data update storage module, used to obtain real-time update data of the data source platform through the data acquisition path, locate the fuel management cycle according to the data factor, and construct a management cycle data block and store it in the data middle platform; a cycle feature analysis module, used to perform feature analysis of the management cycle according to the management cycle data block to obtain cycle fuel features; a supply imbalance analysis module, used to perform full-cycle supply imbalance analysis based on the supply balance influence relationship of the fuel management cycle and the cycle fuel features to obtain imbalance nodes and imbalance features; a balance compensation module, used to perform balance compensation according to the imbalance nodes and imbalance features to obtain a full-cycle balance management strategy.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] Decompose the fuel management cycle and analyze the management objectives of the fuel management cycle, obtain the data factors of the management objectives, and the entire fuel data management process provides clear objectives and data collection directions to ensure the pertinence and effectiveness of data collection. According to the data factors, a data collection channel is established, and a connection is established with the data source platform to achieve real-time data collection and update, and improve the efficiency and accuracy of data processing. Real-time updated data is obtained through the data collection channel, and management cycle data blocks are constructed and stored in the data center, which provides a complete and orderly data foundation for subsequent analysis and helps to grasp the data situation in the fuel management cycle as a whole. In-depth mining of the integrated management cycle data blocks is carried out to identify the key features of each management cycle and obtain cycle fuel features. These features reflect the state, regularity and other important information of the fuel in the management cycle, and provide a basis for subsequent supply imbalance analysis. Based on the cycle fuel characteristics obtained above, the supply imbalance analysis of the whole cycle is carried out in combination with the supply balance impact relationship to find out the imbalance nodes and imbalance features, so as to accurately identify the problems in the fuel supply process and provide key information for balance compensation. Balance compensation is performed according to the imbalance nodes and imbalance characteristics to obtain a full-cycle balance management strategy, realize dynamic adjustment of the supply process, and ensure the balance and stability of the fuel supply.

[0008] In summary, this application decomposes the fuel management cycle and analyzes the target to obtain data factors, establishes a data collection channel to obtain data and constructs a management cycle data block, and then conducts in-depth analysis to obtain the cycle fuel characteristics, further conducts full-cycle supply imbalance analysis, and finally obtains a balance management strategy based on the imbalance situation. This series of steps can accurately collect data related to management goals, improve the efficiency and accuracy of data collection, and can also timely grasp the characteristics of fuel within the management cycle, discover supply imbalance problems from a full-cycle perspective, and formulate effective balance management strategies for imbalance situations, thereby ensuring the stability and continuity of fuel supply and reducing the risks caused by supply imbalances.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flow chart of the method for intelligent management of fuel data based on a data middle platform provided in an embodiment of the present application.

[0011] Figure 2 A flow chart of obtaining data factors of management targets in the intelligent fuel data management method based on a data middle platform provided in an embodiment of the present application.

[0012] Figure 3 A schematic diagram of the process of obtaining imbalance nodes and imbalance characteristics in the fuel data intelligent management method based on the data middle platform provided in an embodiment of the present application.

[0013] Figure 4 A schematic diagram of the structure of the fuel data intelligent management system based on the data middle platform provided in an embodiment of the present application.

[0014] Explanation of the reference numerals: management target analysis module 10 , data acquisition channel establishment module 20 , data update storage module 30 , cycle characteristic analysis module 40 , supply imbalance analysis module 50 , balance compensation module 60 . DETAILED DESCRIPTION

[0015] The embodiments of the present application provide a fuel data intelligent management method and system based on a data middle platform, thereby solving the technical problems that the traditional fuel data management method has a cumbersome data processing process and lacks systematic analysis methods for the fuel management cycle, resulting in the inability to provide accurate data support for fuel supply decision analysis. This achieves the technical effect of improving the efficiency and accuracy of fuel data processing, thereby enhancing the stability and sustainability of the fuel supply throughout the entire cycle.

[0016] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a fuel data intelligent management method based on a data middle platform, the method comprising:

[0017] Step S1: Decompose the fuel management cycle, analyze the management target of the fuel management cycle, and obtain data factors of the management target.

[0018] Specifically, the fuel management cycle refers to the different management intervals in the fuel supply chain management, which are divided according to time or stage. The management objectives refer to the specific goals that need to be achieved in each fuel cycle, such as sufficient supply, reasonable inventory, cost control, etc. Data factors refer to various data elements or variables that are closely related to the management objectives, such as inventory, demand forecast, supplier delivery time, etc.

[0019] The fuel management cycle is divided in detail according to the different stages of fuel supply, including the procurement cycle (from fuel demand forecasting to supplier selection and purchase order generation), transportation cycle (logistics process of fuel from supplier to plant), storage cycle (management of fuel storage in plant), use cycle (fuel blending, unit operation and fuel consumption), etc. Based on management experience and data analysis, the key goals of each management cycle are determined. These goals can be specific requirements on fuel consumption, inventory levels, supply chain efficiency, etc. Then, using data analysis techniques such as data mining and statistical analysis, the data points most relevant to these goals are identified from historical data. These data points are data factors. For example, if the management goal is to reduce fuel consumption, then the data factors may include fuel utilization rate, equipment efficiency and operating conditions. The identified data factors can more accurately reflect the characteristics and needs of each cycle, provide a more accurate basis for subsequent data collection, analysis and other operations, and make the entire fuel data management more in line with the actual business process.

[0020] Step S2: According to the data factor, a data acquisition path is established, the data acquisition path is associated with the data factor mapping, and the data acquisition path uses the data factor as the data acquisition index, and the data acquisition path is used to establish a connection between the data middle platform and the data source platform.

[0021] Specifically, the data collection channel is a specific transmission channel from the data source to the data middle platform established to obtain relevant data for each cycle, ensuring the real-time flow and update of data. First, it is necessary to determine the data source platform, which may include sensors, ERP systems, warehousing systems, logistics management systems, etc. Then, according to the data factors required by the management objectives, multiple data collection channels are built. These channels can collect data from the data source platform in real time and transmit it to the data middle platform for further analysis and processing. There is a mapping relationship between the data factors and data collection channels of each management cycle. The corresponding data collection channel can be located through the data factors, so that data can be collected from different platforms to the data middle platform to ensure that the acquired data is relevant to the management objectives, avoiding cumbersome data screening steps and improving data collection efficiency.

[0022] Step S3: Acquire real-time updated data from the data source platform through the data acquisition channel, locate the fuel management cycle according to the data factors, construct a management cycle data block and store it in the data middle platform.

[0023] Specifically, real-time updated data refers to the latest data obtained from the data source platform. These data usually change in real time and can reflect the actual status of the current fuel supply chain. The management cycle data block refers to the integration of all relevant data of a management cycle into a data unit to facilitate subsequent analysis and processing. The data middle platform is a system used to store, process and analyze data collected from various data sources. All data blocks of management cycles are ultimately stored in the middle platform. The data collection channel will continuously collect data from the data source platform, such as warehouse inventory, transportation status, fuel consumption, etc. And determine the management cycle corresponding to the data based on the data factors, and classify and store the data in the corresponding area of ​​the data middle platform. These data will be organized into data blocks, each block corresponds to a management cycle, and contains all relevant data factors within the cycle.

[0024] Through real-time collection and construction of management cycle data blocks, it can be ensured that data from different periods are accurately classified and stored. The formed management cycle data blocks can comprehensively and accurately reflect the actual situation of each period, providing a rich and orderly data basis for subsequent analysis of each period.

[0025] Step S4: performing characteristic analysis of the management cycle according to the management cycle data block to obtain cycle fuel characteristics.

[0026] Specifically, the cycle fuel characteristics are the unique attributes of the fuel in each management cycle data block, such as the supplier price fluctuation trend in the procurement cycle, the transportation stability in the transportation cycle, etc. The data in the management cycle data block is deeply analyzed to find the key characteristics and rules in the cycle. The characteristics related to fuel supply in each cycle are extracted to provide a basis for subsequent decision-making. For example, for the data block of the procurement cycle, data analysis software can be used for analysis, and the average value, fluctuation range and other characteristics of the supplier's quotation can be obtained through statistical analysis methods. This is the cycle fuel characteristics of the procurement cycle; in the transportation cycle, the punctuality of transportation, the stability of the transportation route and other characteristics can be obtained by analyzing the data such as transportation location and speed, for example, using the trajectory analysis algorithm; for the storage cycle, the inventory turnover rate, fuel quality stability and other characteristics can be obtained by analyzing the inventory data and quality inspection data; for the use cycle, the fuel utilization efficiency and other cycle fuel characteristics can be obtained based on the analysis of fuel consumption and unit operation parameters.

[0027] By deeply mining the periodic fuel characteristics from the data blocks of each period, we can clearly understand the status and characteristics of the fuel in each period, provide a detailed basis for the analysis of the supply imbalance of the whole period, and help to grasp the fuel management situation more comprehensively.

[0028] Step S5: Based on the supply balance influence relationship of the fuel management cycle, a full-cycle supply imbalance analysis is performed according to the cycle fuel characteristics to obtain imbalance nodes and imbalance characteristics.

[0029] Specifically, the supply balance influencing relationship refers to the relationship in which the factors in each cycle affect the fuel supply balance during the entire fuel management process. For example, the supplier selection in the procurement cycle will affect the transportation arrangement in the transportation cycle, which in turn affects the inventory in the storage cycle and the fuel supply stability in the use cycle. The imbalance node refers to the specific link or connection point where a supply imbalance occurs in a cycle or between multiple cycles in the entire fuel management process. The imbalance characteristics are phenomena such as supply shortages, inventory backlogs, and excessive costs that appear at these imbalance nodes.

[0030] Based on the supply balance impact relationship, combined with the cycle fuel characteristics of each cycle, the nodes and links that may cause imbalance are analyzed to identify the characteristics that may appear at the imbalance node, such as inventory decline, transportation delay, etc. For example, if the cycle fuel characteristics of the procurement cycle show that the supplier's price continues to rise and the supply is unstable, and the transportation punctuality of the transportation cycle is poor, it can be determined that the procurement and transportation links may be imbalance nodes, and unstable supply and unpunctual transportation are imbalance characteristics. Through imbalance analysis, potential risk nodes in fuel management can be identified in advance, providing early warning for subsequent balance management and reducing fluctuations in fuel supply.

[0031] Step S6: Perform balance compensation according to the imbalance nodes and imbalance characteristics to obtain a full-cycle balance management strategy.

[0032] Specifically, the full-cycle balance management strategy covers all cycles of fuel management and is a set of management plans and measures formulated to maintain the balance of fuel supply, aiming to restore the balance of fuel supply between cycles.

[0033] According to the identified imbalance nodes and characteristics, formulate corresponding compensation measures, including adjusting production plans, changing inventory strategies, optimizing logistics routes, or negotiating with suppliers to ensure supply stability. According to the supply balance analysis results of the whole cycle, formulate a detailed balance management strategy to optimize each link of fuel procurement, storage, transportation and use to ensure the stability of fuel supply. By formulating a full-cycle balance management strategy, it is possible to comprehensively adjust and optimize the imbalance problems in the fuel management process, ensure the balance of fuel supply between each cycle, improve the overall efficiency and stability of fuel management, and reduce operating costs.

[0034] Further, such as Figure 2 As shown, step S1 of the embodiment of the present application includes:

[0035] Step S11: obtaining positive samples and negative samples of the fuel management cycle, wherein the positive samples are cases where the evaluation results of the fuel management cycle reach the target threshold, and the negative samples are cases where the evaluation results do not reach the target threshold.

[0036] Step S12: extracting management target events according to the positive sample and the negative sample respectively, and performing influencing factor analysis on the management target events to obtain positive factor analysis results and negative factor analysis results.

[0037] Step S13: Taking the management target event as the alignment condition, align and fuse the positive example factor analysis result and the negative example factor analysis result, take the management target event as the management target, integrate the corresponding data types of the fused influencing factors, and obtain the data factor of the management target.

[0038] Specifically, positive samples are cases in which the evaluation results reach the pre-set target threshold during the fuel management cycle. For example, in the fuel management of thermal power generation, if the set target threshold is that the number of fuel supply interruptions does not exceed 3 times and the cost is controlled within the budget, then the fuel management cycle cases that meet this condition are positive samples. Negative samples are the opposite of positive samples. They refer to cases in which the evaluation results do not reach the target threshold during the fuel management cycle. For example, cases where the number of fuel supply interruptions exceeds 3 times or the cost exceeds the budget. The target threshold is a set standard used to measure whether the fuel management goal has been achieved.

[0039] First, determine the criteria for evaluating the success of the fuel management cycle, i.e., the target threshold. The target threshold can be the upper limit of the number of interruptions in fuel supply, the upper limit of cost, etc. Then, filter out cases that meet the definition of positive and negative samples from the historical fuel management data. The screening process can use data mining tools, such as SQL query statements, to extract relevant data from the database. For example, by writing SQL query statements, positive and negative samples can be filtered out according to the set evaluation indicators (such as whether the cost is within the budget, etc.).

[0040] Management target events refer to specific events related to management targets in the fuel management cycle, such as bidding events in fuel procurement, delivery events in transportation, etc. These events have a direct or indirect impact on management targets. The positive factor analysis results are the results obtained after the impact factor analysis of the management target events in the positive sample, which includes the various influencing factors in the case of successfully achieving the management target. The negative factor analysis results are the results of the impact factor analysis of the management target events in the negative sample, which reflects the influencing factors in the case of not achieving the management target.

[0041] Conduct in-depth analysis on each positive sample and negative sample to extract events related to fuel management goals, i.e., management target events. Identify the key factors that affect these management target events and determine the positive factor analysis results and negative factor analysis results. For example, the factors in the positive sample may be "timely delivery by suppliers" and "optimization of inventory management system", while the factors in the negative sample may be "transportation delays caused by weather reasons" and "inadequate production capacity of suppliers". The analysis process can use tools such as cause-and-effect analysis diagrams or accident trees.

[0042] Taking the management target event as the alignment condition, the influencing factors in the positive example factor analysis results and the negative example factor analysis results are compared one by one. For example, under the management target event of procurement bidding, the supplier reputation in the positive example factor analysis results is compared with the supplier reputation in the negative example factor analysis results. Then, similar influencing factors are fused to remove duplicate and redundant parts. For cases where the data types are different but represent the same influencing factor, the data types are integrated. For example, the supplier reputation in the positive example factor analysis results is expressed as a grade, and in the negative example factor analysis results it is expressed as a score, so they need to be integrated into a unified data type. Through factor alignment and fusion, a comprehensive set of data factors is formed, which can comprehensively reflect the various factors that affect the achievement of fuel management goals.

[0043] Through factor alignment and fusion, a more accurate and comprehensive set of influencing factors can be obtained, which provides a precise and unified data basis for subsequent fuel management data collection, analysis and other operations, and improves the accuracy and efficiency of the entire fuel management data processing.

[0044] Furthermore, in step S12, management target events are extracted according to the positive sample and the negative sample, and then the following is further included:

[0045] Step S121: Segment the fuel management cycle into operation steps, obtain target events generated by each operation step, and summarize the target event set of the operation steps.

[0046] Step S122: traverse the management target events by using the operation step target event set to obtain the missing step target events.

[0047] Step S123: supplement the management target event with the missing step target event.

[0048] Specifically, the step-generated target event is an event related to the management target generated during the execution of each operation step. For example, in the bidding operation step, successfully attracting a certain number of qualified suppliers to participate in the bidding is a step-generated target event. The operation step target event set is a set formed by summarizing the target events generated by all operation steps. According to the actual business logic of the fuel management cycle, each link or stage in the fuel management cycle is further decomposed into specific operation steps. For example, the procurement cycle can be decomposed into multiple specific steps such as demand forecasting, supplier selection, and purchase order generation. For each operation step, analyze the target event that should be generated under normal operation. For example, in the vehicle scheduling step, timely dispatching to a suitable transport vehicle is a target event. Summarize the target events of each operation step to form an operation step target event set. Through the segmentation of operation steps and the aggregation of target events, the target events of each link in the fuel management cycle can be comprehensively sorted out, providing a detailed basis for the subsequent supplementation and improvement of management target events.

[0049] With the operation step target event set as a reference, the extracted management target events are traversed and checked, and each event in the operation step target event set is compared with the management target event. The target events that are missing in the management target event but exist in the operation step target event set are identified and defined as missing step target events. For example, if there is a regular inventory count event in the fuel storage management cycle but it is not in the management target event, then this regular inventory count event is a missing step target event.

[0050] According to the identified missing step target events, corresponding events are obtained from historical data to supplement the extracted management target events. The supplemented events are reintegrated to form a complete set of management target events. Ensure that the key target events of each operation step are included in the management target events to provide comprehensive data support. For example, if it is found that the fuel quality real-time monitoring event in the fuel use cycle is a missing step target event, retrieve the event from historical data and add it to the management target event.

[0051] By supplementing the missing step target events, the management target events are improved, so that the management target events can more comprehensively reflect all aspects of the fuel management cycle, providing a more complete basis for the subsequent analysis of influencing factors, thereby more accurately identifying the various factors that affect the realization of management goals.

[0052] Furthermore, in step S12, the impact factor analysis is performed on the management target event to obtain the positive example factor analysis result and the negative example factor analysis result, including:

[0053] Step S124: performing event correlation analysis on the management target event to determine intermediate events and basic events.

[0054] Step S125: Decompose the event factors layer by layer in the order from the intermediate event to the basic event to determine the event impact factors and their impact relationships.

[0055] Step S126: construct an event parsing tree according to the hierarchical relationship of intermediate event-basic event-event impact factor.

[0056] Step S127: Based on the event influencing factors and their influencing relationships, verify the event occurrence probability from bottom to top layer by layer according to the event parsing tree in accordance with the logic gate relationship. When the probability threshold requirement is reached, determine the event influencing factors and their influencing relationships to obtain the factor parsing results.

[0057] Specifically, an intermediate event is an event in the causal chain of the management target event that is affected by other events and affects other events, and is in the middle link. For example, in fuel supply management, the transportation scheduling event is affected by the fuel purchase volume and affects the arrival time of the fuel, so it is determined to be an intermediate event. The basic event is the first event that occurs in the management target event and will have an initial impact on other events. For example, the fuel demand forecast event is a basic event in fuel management, which will affect a series of subsequent events such as procurement and transportation.

[0058] Data mining technology is used to analyze management target events. For example, by analyzing historical fuel management data, the order of events and the correlation coefficients between events can be checked. If two events often occur at the same time or one event has a higher probability of occurring after the other event, then there is a correlation between the two events. Through event correlation analysis, it is determined which are intermediate events and which are basic events, and the internal logical structure of management target events is sorted out, which provides a clear framework for subsequent event factor decomposition and helps to more specifically identify various factors that affect management target events.

[0059] Event influencing factors are various factors that affect the occurrence and results of events found in the process of event factor decomposition. For example, in the transport scheduling event, the number of transport vehicles, the availability of drivers, etc. are event influencing factors. Factor decomposition is performed on each event in the order from intermediate events to basic events. Through data analysis, historical cases and expert knowledge, the root cause of each event is analyzed layer by layer, the influencing factors of each event are identified, and the influence relationship between these influencing factors and events is analyzed. For example, when analyzing the intermediate event of transport scheduling, it is found that the number of transport vehicles has a direct positive correlation with the success of transport scheduling, that is, the more vehicles there are, the higher the probability of successful scheduling. Through layer-by-layer factor decomposition, the specific causes of each event can be fully identified, and the relationship between the influencing factors can be revealed, providing a detailed basis for further factor modeling and event prediction.

[0060] The event parsing tree is a graphical data structure used to represent the hierarchical relationship between events. The hierarchical relationship refers to the superior-subordinate relationship between events and factors. In the parsing tree, the basic event is located at the root of the tree, the intermediate event is located at the branch of the tree, and the event factor is located at the end of the tree. According to the intermediate events, basic events, event influencing factors and their influencing relationships determined earlier, the event parsing tree is constructed according to the hierarchical relationship of intermediate events-basic events-event influencing factors, which intuitively displays the hierarchical structure and mutual relationship between events. Taking the supply management in fuel management as an example, transportation scheduling (intermediate event) is a branch node of the tree, fuel demand forecasting (basic event) is a child node under the transportation scheduling node, and event influencing factors such as the number of transportation vehicles and driver availability are leaf nodes under the fuel demand forecasting node. The event parsing tree presents the complex relationship of management target events in an intuitive tree structure, which can clearly display the hierarchical relationship between various events and influencing factors, helps to grasp the structure of management target events as a whole, and provides a clear framework for subsequent event probability verification.

[0061] The logic gate relationship is a rule used to represent the logical relationship between event influencing factors, basic events, and intermediate events in the event parsing tree. The probability threshold is a pre-set probability value. When the verified probability of an event reaches this value, it is considered that the event influencing factor has sufficient influence on the event.

[0062] Starting from the leaf nodes (event impact factors) of the event parsing tree, the probability of each node to the upper layer of events is calculated based on the logic gate relationship. For example, if the occurrence of a basic event requires two event impact factors to be satisfied at the same time (and relationship), the probability of the occurrence of the basic event is calculated based on the separate probabilities of the two event impact factors. The calculated probability is then passed upward layer by layer until the probability of the intermediate event is calculated. This process can use a probability calculation model, such as a Bayesian network model, to perform probability calculations. When the calculated probability of an event reaches the pre-set probability threshold requirement, it is determined that the event impact factor and its impact relationship at this time have a significant impact on the management target event, and it is used as the factor parsing result. By verifying the probability of event occurrence from bottom to top and layer by layer, it is possible to determine reasonable event impact factors and their impact relationships based on actual data and logical relationships, ensure the accuracy and reliability of the factor parsing results, and provide a scientific basis for subsequent fuel management decisions.

[0063] Furthermore, in step S127, when the probability threshold requirement is not met, the method further includes:

[0064] Step S127 - 1 : Obtain an abnormal event, where the abnormal event is an intermediate event or a basic event whose logic gate relationship verification result does not reach a probability threshold.

[0065] Step S127-2: extracting a historical event record data set based on the abnormal event, performing semantic mining on the historical event record data set, and establishing a factor relationship graph for reflecting the semantic association between factors.

[0066] Step S127-3: Based on the factor relationship map, mining explicit factors and latent factors.

[0067] Step S127 - 4 : fitting the correlation and influence relationship between the explicit factor, the implicit factor and the abnormal event according to the historical event record data set.

[0068] Step S127-5: Add the associated impact relationship to the logic gate relationship, and perform reverse verification from bottom to top layer by layer based on the event parsing tree until the probability of event occurrence reaches the probability threshold requirement.

[0069] Specifically, in the probability verification process of step S127, when the calculated probability of occurrence of a certain intermediate event or basic event does not meet the probability threshold requirement, the event is marked as an abnormal event. Under normal logical relationships, the probability of occurrence of these abnormal events does not meet expectations, and there may be special influencing factors that require further analysis.

[0070] The historical event record dataset is a data set containing various event records related to fuel management that occurred in the past. These records can be detailed information about various links such as fuel procurement, transportation, storage and use. The factor relationship map is a map constructed through semantic mining, which is used to show the semantic association relationship between factors (event influencing factors) to intuitively present the connection between different factors at the semantic level. Accurately identifying abnormal events provides a clear goal for subsequent in-depth analysis, helps to find out the potential reasons why the probability of an event does not meet expectations, and thus further improves the analysis of event influencing factors and their influence relationships.

[0071] Obtain a data set of historical event records related to abnormal events from the database. For the text information in the data set (such as event descriptions, notes, etc.), use natural language processing technology to perform semantic mining analysis to mine potential influencing factors and their semantic associations. For example, use the word vector model to convert the text into a vector representation, and then use algorithms such as cluster analysis and association rule mining to extract the semantic associations between factors and construct a factor relationship map. The factor relationship map reflects the correlation and influence between each factor, providing a structured diagram for subsequent factor analysis.

[0072] Explicit factors are factors that can be directly observed to have obvious correlations with abnormal events in historical event record data sets through semantic mining and other methods. For example, in abnormal fuel transportation events, transportation vehicle failure records frequently appear, and the condition of the transportation vehicle is an explicit factor. Hidden factors are factors that have a potential correlation with abnormal events, but are not easy to find directly in the data set and need to be mined through in-depth analysis of semantic relationships and other methods. For example, in the same abnormal transportation event, road construction information around the transportation route may be hidden in the event description. After semantic mining, it is found that it is associated with transportation anomalies. This is a hidden factor. According to the constructed factor relationship graph, explicit factors and hidden factors are mined by analyzing indicators such as the connection strength and semantic relevance between factors. Factors with high connection strength and direct semantic relevance are determined to be explicit factors; factors with weak connection strength but related to abnormal events through multi-step semantic associations are determined to be hidden factors. The analysis process can use graph analysis algorithms, such as the PageRank algorithm, to measure the connection strength between factors and assist in mining explicit and hidden factors. Uncovering explicit and implicit factors helps to consider the factors that affect abnormal events more comprehensively, not just the factors that are easy to find on the surface, and provides richer materials for further analysis of the causes of abnormal events.

[0073] Perform statistical analysis and data fitting operations on the historical event record data set. For example, for abnormal fuel transportation events, take the extension of transportation time as the abnormal event, the number of transportation vehicle failures (explicit factors) and road construction conditions (implicit factors) as independent variables, and build a regression model (such as a linear regression model) to fit the correlation and influence relationship between them and the extension of transportation time. By fitting the correlation and influence relationship, the influence of explicit factors and implicit factors on abnormal events can be quantified, making the subsequent probability verification more accurate.

[0074] The obtained associated influence relationship is added to the original logic gate relationship, and the event parsing tree is reconstructed. Then, according to the bottom-up reverse layer-by-layer verification method in step S127, the probability of event occurrence is recalculated. For example, if the original logic gate relationship does not consider the impact of road construction conditions (hidden factors) on the extension of transportation time (abnormal event), after adding the associated influence relationship, the probability of occurrence of the abnormal event of extended transportation time is calculated again from the event influence factor until the probability reaches the probability threshold requirement. By continuously adjusting the logic gate relationship and re-verifying the probability of event occurrence, the analysis of event influence factors and their influence relationships can be gradually improved, so that the final result is more in line with the actual situation, and the accuracy and reliability of the analysis of fuel management events are improved.

[0075] Further, such as Figure 3 As shown, step S5 of the embodiment of the present application includes:

[0076] Step S51: Setting the cycle balance target relationship and penalty conditions of the fuel management cycle.

[0077] Step S52: Analyze the characteristic relationship between fuel management cycles according to the cycle balance target relationship.

[0078] Step S53: constructing an evaluation function according to the feature relationship and penalty conditions.

[0079] Step S54: using the evaluation function to evaluate the balance target relationship of the periodic fuel characteristics to obtain a periodic node evaluation value.

[0080] Step S55: locating the imbalance node according to the periodic node evaluation value, and locating the imbalance feature in combination with the periodic balance target relationship.

[0081] Specifically, the cycle balance target relationship is a target relationship that is expected to be established between the various cycles in the fuel management cycle in order to achieve overall balance. The penalty condition is the condition or rule set to measure the degree of deviation when the actual situation in the fuel management cycle deviates from the cycle balance target relationship. It can be a specific numerical limit, time limit or resource limit, etc.

[0082] According to the overall goal of fuel management and the needs and expectations of each link in the entire management cycle, the cycle balance target relationship is set. This cycle balance target relationship can be dynamically adjusted according to actual needs. For example, based on historical data and the company's production plan, determine the reasonable proportional relationship between the purchase volume in the procurement cycle and the usage volume in the use cycle. Set penalty conditions based on the company's internal cost accounting system and risk management requirements. For example, based on storage costs and safety stock considerations, set penalty conditions corresponding to the upper and lower limits of storage cycle inventory. Setting cycle balance target relationships and penalty conditions provides standards and basis for subsequent analysis and evaluation, helps to standardize the fuel management process, promptly discover and correct possible imbalances, and improve the efficiency and benefits of fuel management.

[0083] The characteristic relationship is based on the cycle balance target relationship, and is the relationship between the various characteristics exhibited by each fuel management cycle in the actual operation process. For example, the price fluctuation characteristics of the procurement cycle may affect the transportation volume selection characteristics of the transportation cycle, which is a characteristic relationship. According to the previously set cycle balance target relationship, the actual operation data of each fuel management cycle is analyzed. Data analysis methods such as correlation analysis and regression analysis can be used. Taking the procurement cycle and transportation cycle as an example, the characteristic relationship between the two is determined by analyzing the correlation between the procurement price and the transportation volume in the historical data. By analyzing the characteristic relationship, we can deeply understand the internal connection between the various fuel management cycles, provide the necessary input for constructing the evaluation function, and help to more accurately evaluate the balance status of the fuel management cycle.

[0084] The evaluation function is a mathematical function constructed based on characteristic relationships and penalty conditions, and is used to quantitatively evaluate the balance status of the fuel management cycle. The evaluation function is constructed based on the characteristic relationships obtained by analysis and the set penalty conditions. For example, the evaluation function can be Among them, ω i The weight of the i-th feature reflects the importance of the feature in the evaluation function. i is the actual observed or calculated value of the ith feature. i目标 is the target value of the ith feature. (x i -x i目标 ) 2 It is used to measure the deviation between the feature value and the target value. The square form ensures that the deviation value is non-negative and large deviations will be amplified. j ) is a function related to the penalty condition, which indicates the penalty value for certain conditions in the cycle (such as fuel shortage or excess). n is the total number of features, and m is the total number of penalty conditions. (x)The smaller it is, the closer it is to the balance target relationship. The evaluation function provides a quantitative evaluation standard for the balance status of the fuel management cycle, which can conveniently and quickly evaluate the fuel management under different circumstances and provide a powerful tool for discovering imbalance nodes and imbalance characteristics.

[0085] The cycle node evaluation value is the value obtained by evaluating the cycle fuel characteristics of each fuel management cycle using the evaluation function. This value reflects the performance of each cycle in the balance target relationship. Substitute the cycle fuel characteristic data of each fuel management cycle into the evaluation function for calculation, and calculate the cycle node evaluation value of each cycle respectively. By calculating the cycle node evaluation value, the balance status of each fuel management cycle can be quantitatively evaluated, which provides a direct data basis for locating imbalance nodes and helps to accurately identify the problematic links in the fuel management process.

[0086] Compare and analyze based on the calculated cycle node evaluation values. If the cycle node evaluation value of a certain cycle is significantly lower than that of other cycles or lower than the preset threshold, then this cycle may be an unbalanced node. Then, further analyze the specific unbalanced characteristics of the unbalanced node in combination with the cycle balance target relationship. For example, based on the balance target relationship between the procurement cycle and other cycles, if it is found that the procurement volume is far lower than the demand for usage, then "insufficient procurement volume" is the unbalanced characteristic of the unbalanced node (procurement cycle). By locating the unbalanced nodes and unbalanced characteristics in the fuel management process, a clear direction is provided for the subsequent balance compensation measures, which helps to improve the overall balance and efficiency of fuel management.

[0087] Furthermore, step S6 of the embodiment of the present application also includes:

[0088] Step S61: forecasting long-term and short-term supply and demand according to the periodic fuel characteristics, and establishing a supply timing chain and a demand timing chain.

[0089] Step S62: Based on the connection relationship of the fuel management cycle, the supply timing chain and the demand timing chain are aligned to construct the supply and demand timing chain between cycle nodes.

[0090] Step S63: predicting the supply-demand balance relationship according to the supply-demand timing chain to obtain a predicted imbalance timing node.

[0091] Step S64: Based on the predicted imbalanced timing nodes, timing constraint conditions are analyzed according to the timing distance and the supply timing characteristics of the periodic fuel characteristics to obtain the minimum adjustment time window.

[0092] Step S65: taking the adjusted minimum time window as a constraint condition to perform balance compensation on the unbalanced timing nodes.

[0093] Specifically, by analyzing historical data and related factors, the supply and demand quantities of fuel in longer time periods (such as January and quarter) and shorter time periods (such as three days and one week) are estimated, and the estimated long-term and short-term supply and demand quantities are arranged in chronological order to form a supply time series chain and a demand time series chain. Among them, the supply time series chain reflects the quantity and source of fuel supply at different time points. The demand time series chain shows the quantity, purpose and other information of fuel demand at different time points. For the forecast of supply and demand, forecasting algorithms (such as time series analysis, regression analysis, etc.) can be used to complete it. Taking fuel demand forecasting as an example, if there is fuel consumption data for many years in the past, by fitting the ARIMA model, the fuel demand for the next year can be predicted. For short-term forecasting, it can be combined with recent actual conditions, such as current production plans, equipment operating status and other factors, and forecasting can be carried out by using moving average method or exponential smoothing method. Through long-term and short-term forecasts of supply and demand, a more accurate future view can be provided for fuel management, helping to identify potential supply imbalance problems and providing data support for subsequent adjustments and compensation.

[0094] According to the connection relationship of the fuel management cycle, the corresponding relationship between each node in the supply timing chain and the demand timing chain is determined to ensure the matching of supply and demand information at the same time point. After the supply timing chain and the demand timing chain are aligned, a supply and demand timing chain is formed, which accurately reflects the changes in the supply and demand relationship of fuel at each cycle node over time.

[0095] The predicted imbalance time series node is a periodic node that is judged to be unbalanced between supply and demand at a certain point in the future in the supply and demand balance relationship forecast. For each periodic node in the supply and demand time series chain, the quantity relationship between supply and demand is compared. A balance threshold can be set, and when the difference between supply and demand exceeds this threshold, it is judged to be unbalanced. For example, if the difference between supply and demand is greater than 10% of the total demand, the node is considered to be unbalanced. By traversing all nodes in the supply and demand time series chain, find the node that meets the imbalance condition, that is, the predicted imbalance time series node.

[0096] The time series distance is the time interval between the predicted imbalance time series node and other related nodes in the supply and demand time series chain. The supply time series characteristics are the characteristics of fuel supply in the time series, such as the periodicity, seasonality, volatility, etc. of the supply. The minimum time window for adjustment is the shortest time range required to balance and compensate the imbalance time series nodes under various time series constraints.

[0097] First, determine the time series distance between the predicted imbalance timing node and other related nodes. For example, in fuel supply management, if a storage cycle node is predicted to be unbalanced within the next month, it is necessary to analyze the time interval between this node and the procurement cycle node (supply source). Then, analyze the supply timing characteristics combined with the cycle fuel characteristics, and parse the timing constraints by establishing a mathematical model or rule set to determine the minimum adjustment time window. For example, a linear programming model can be established based on historical data, with supply timing characteristics and timing distance as constraints. The goal is to minimize the adjustment time and solve the minimum adjustment time window.

[0098] The minimum adjustment time window is used as a constraint to adjust the imbalanced timing nodes. If the imbalanced timing node is a case of insufficient supply, measures such as increasing purchase volume and speeding up transportation can be taken within the minimum adjustment time window. For example, if it is predicted that the fuel inventory is insufficient in a certain weekly storage cycle, and the minimum adjustment time window is one week, additional purchase orders can be arranged within this week or the transportation route can be optimized to improve transportation efficiency.

[0099] The above steps obtain the predicted imbalance time series nodes by analyzing the supply and demand balance relationship prediction, which can detect the supply and demand imbalance that may occur in the fuel management cycle in advance, so that preventive measures can be taken in advance to compensate for the balance and improve the stability and efficiency of fuel management.

[0100] In summary, the fuel data intelligent management method based on the data middle platform provided in the embodiment of the present application has the following technical effects:

[0101] By decomposing the fuel management cycle and analyzing the management objectives, fuel supply management is divided into multiple management cycles, identifying and focusing on solving the most critical problems in each management cycle. By clarifying the management objectives, it is ensured that the data collection and analysis of each cycle can be targeted, and the accuracy and effectiveness of data processing can be improved. By establishing data collection channels and data factor mapping, the connection between the data source platform and the data middle platform is more efficient, ensuring that key data factors related to management objectives are automatically collected from different data source platforms, avoiding the tedious process of manually collecting and screening data in traditional methods, and improving the efficiency and accuracy of data collection. The real-time updated data of the source platform is obtained through the data collection channel, and the fuel management cycle is located based on the data factors. The cycle management data block is constructed, and the data from multiple data sources is integrated to form a detailed data view of the management cycle, providing a high-quality data foundation for subsequent feature analysis and decision-making. By performing feature analysis on the management cycle data block, the cyclical characteristics of fuel supply are revealed, providing a scientific basis for the stability and risk management of each link of fuel supply. Combined with the analysis of the entire cycle, potential supply imbalance nodes and their characteristics can be identified, thereby providing an early warning mechanism for balance compensation and risk control. Finally, a full-cycle balance management strategy is formulated based on the imbalance nodes and imbalance characteristics. Through this strategy, fuel supply plans and management measures can be adjusted in a targeted manner to ensure the balance and stability of the full-cycle supply chain and avoid the risk of oversupply or shortage.

[0102] Overall, the embodiments of the present application improve the efficiency and accuracy of data processing by periodizing fuel management, automating data collection channels, extracting periodic features, and analyzing supply imbalances, thereby ensuring accurate decision-making throughout the entire management cycle. This method can acquire and analyze fuel supply chain data in real time, provide managers with reliable decision-making support, identify potential risks in a timely manner, and implement dynamic adjustments, which not only improves the management efficiency of the fuel supply chain, but also enhances the ability to respond to market fluctuations and supply imbalances, and ensures the stability and continuity of fuel supply throughout the entire cycle.

[0103] Embodiment 2, as Figure 4 As shown, the embodiment of the present application provides a fuel data intelligent management system based on a data middle platform, and the system includes:

[0104] The management target parsing module 10 is used to decompose the fuel management cycle, parse the management target of the fuel management cycle, and obtain data factors of the management target.

[0105] The data acquisition path establishment module 20 is used to establish a data acquisition path according to the data factor. The data acquisition path is associated with the data factor mapping, and the data acquisition path uses the data factor as the data acquisition index. The data acquisition path is used to establish a connection between the data middle platform and the data source platform.

[0106] The data update storage module 30 is used to obtain real-time update data of the data source platform through the data acquisition channel, locate the fuel management cycle according to the data factors, and construct a management cycle data block to store it in the data middle platform.

[0107] The cycle characteristic analysis module 40 is used to perform characteristic analysis of the management cycle according to the management cycle data block to obtain cycle fuel characteristics.

[0108] The supply imbalance analysis module 50 is used to perform a full-cycle supply imbalance analysis based on the supply balance influence relationship of the fuel management cycle and the cycle fuel characteristics to obtain imbalance nodes and imbalance characteristics.

[0109] The balance compensation module 60 is used to perform balance compensation according to the imbalance node and the imbalance characteristics to obtain a full-cycle balance management strategy.

[0110] Furthermore, the management target parsing module 10 of the embodiment of the present application is also used to perform the following steps:

[0111] Positive samples and negative samples of the fuel management cycle are obtained, wherein the positive samples are cases in which the evaluation results of the fuel management cycle reach the target threshold, and the negative samples are cases in which the evaluation results do not reach the target threshold; management target events are extracted according to the positive samples and negative samples, and the management target events are analyzed for influencing factors to obtain positive factor analysis results and negative factor analysis results; taking the management target events as alignment conditions, the positive factor analysis results and the negative factor analysis results are factor-aligned and fused, the management target events are used as the management targets, the corresponding data types of the fused influencing factors are integrated, and the data factors of the management targets are obtained.

[0112] Furthermore, after extracting management target events according to the positive sample and the negative sample, the management target parsing module 10 is further used to perform the following steps:

[0113] The fuel management cycle is divided into operation steps, the target events generated by each operation step are obtained, and the operation step target event set is summarized; the management target events are traversed for missing steps using the operation step target event set to obtain missing step target events; and the management target events are supplemented using the missing step target events.

[0114] Furthermore, the management target parsing module 10 of the embodiment of the present application is also used to perform the following steps:

[0115] Perform event correlation analysis on the management target event to determine intermediate events and basic events; perform event factor decomposition layer by layer in the order from the intermediate event to the basic event to determine event influencing factors and their influencing relationships; construct an event parsing tree according to the hierarchical relationship of intermediate events - basic events - event influencing factors; based on the event influencing factors and their influencing relationships, perform reverse verification of event occurrence probability from bottom to top layer by layer according to the event parsing tree according to the logic gate relationship; when the probability threshold requirement is reached, determine the event influencing factors and their influencing relationships to obtain factor parsing results.

[0116] Furthermore, when the probability threshold requirement is not met, the management target parsing module 10 is further configured to perform the following steps:

[0117] Obtain an abnormal event, wherein the abnormal event is an intermediate event or a basic event whose logic gate relationship verification result does not reach a probability threshold; extract a historical event record data set based on the abnormal event, perform semantic mining on the historical event record data set, and establish a factor relationship map for reflecting the semantic association between factors; based on the factor relationship map, mine explicit factors and implicit factors; fit the association and influence relationship between the explicit factors, implicit factors and the abnormal event according to the historical event record data set; add the association and influence relationship to the logic gate relationship, and perform reverse verification from bottom to top layer by layer based on the event parsing tree until the probability of the event reaching the probability threshold requirement.

[0118] Furthermore, the supply imbalance analysis module 50 of the embodiment of the present application is also used to perform the following steps:

[0119] Set the periodic balance target relationship and penalty conditions of the fuel management cycle; parse the characteristic relationship between the fuel management cycles according to the periodic balance target relationship; construct an evaluation function according to the characteristic relationship and penalty conditions; use the evaluation function to evaluate the balance target relationship of the periodic fuel characteristics to obtain a periodic node evaluation value; locate the imbalance node according to the periodic node evaluation value, and locate the imbalance feature in combination with the periodic balance target relationship.

[0120] Furthermore, the balance compensation module 60 in the embodiment of the present application is also used to perform the following steps:

[0121] According to the characteristics of the cyclic fuel, long-term and short-term supply and demand forecasts are made, and a supply timing chain and a demand timing chain are established; based on the connection relationship of the fuel management cycle, the supply timing chain and the demand timing chain are aligned to build a supply and demand timing chain between cycle nodes; according to the supply and demand timing chain, the supply and demand balance relationship is predicted to obtain a predicted imbalance timing node; based on the predicted imbalance timing node, the timing constraint condition is analyzed according to the timing distance and the supply timing characteristics of the cyclic fuel characteristics to obtain an adjustment minimum time window; the adjustment minimum time window is used as a constraint condition to balance and compensate the imbalance timing node.

[0122] Through the above-mentioned detailed description of the intelligent management method of fuel data based on the data middle platform in this specification, those skilled in the art can clearly understand the intelligent management system of fuel data based on the data middle platform in this embodiment. For the system disclosed in Example 2, since it corresponds to the method disclosed in Example 1 and has corresponding functional modules and beneficial effects, please refer to the method part for relevant details.

[0123] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. The intelligent fuel data management method based on the data center is characterized by: The method comprises: Decomposing a fuel management cycle, analyzing a management target of the fuel management cycle, and obtaining data factors of the management target; According to the data factor, a data collection path is established, the data collection path is associated with the data factor mapping, and the data collection path uses the data factor as a data collection index, and the data collection path is used to establish a connection between the data middle platform and the data source platform; Acquire real-time updated data from the data source platform through the data acquisition channel, locate the fuel management cycle according to the data factor, and construct a management cycle data block to store in the data middle platform; Performing characteristic analysis of the management cycle according to the management cycle data block to obtain cycle fuel characteristics; Based on the supply balance influence relationship of the fuel management cycle, a full-cycle supply imbalance analysis is performed according to the cycle fuel characteristics to obtain imbalance nodes and imbalance characteristics; Balance compensation is performed according to the imbalance nodes and imbalance characteristics to obtain a full-cycle balance management strategy.

2. The method for intelligent fuel data management based on a data middle station as claimed in claim 1, characterized in that: Parsing the management objectives of the fuel management cycle to obtain data factors of the management objectives includes: Obtaining positive samples and negative samples of the fuel management cycle, wherein the positive samples are cases in which the evaluation results of the fuel management cycle reach the target threshold, and the negative samples are cases in which the evaluation results do not reach the target threshold; Extracting management target events according to the positive sample and the negative sample, and analyzing the influencing factors of the management target events to obtain positive factor analysis results and negative factor analysis results; Taking the management target event as the alignment condition, the positive example factor analysis result and the negative example factor analysis result are factor aligned and fused, the management target event is used as the management target, the corresponding data types of the fused influencing factors are integrated to obtain the data factor of the management target.

3. The method for intelligent fuel data management based on a data middle station as claimed in claim 2, characterized in that: Management target events are extracted according to the positive samples and the negative samples respectively, and then the following steps are further included: Segmenting the fuel management cycle into operation steps, obtaining target events generated by each operation step, and summarizing a set of target events of the operation steps; Using the operation step target event set to perform missing traversal on the management target event to obtain the missing step target event; The management target event is supplemented by the missing step target event.

4. The method for intelligent fuel data management based on a data middle station as claimed in claim 2, characterized in that: Performing influencing factor analysis on the management target event to obtain positive example factor analysis results and negative example factor analysis results includes: Conduct event correlation analysis on the management target events to determine intermediate events and basic events; According to the sequence from the intermediate event to the basic event, event factor decomposition is performed layer by layer to determine event influencing factors and their influencing relationships; Construct an event parsing tree according to the hierarchical relationship of intermediate events, basic events, and event impact factors; Based on the event influencing factors and their influencing relationships, the event occurrence probability is verified layer by layer from bottom to top according to the event parsing tree in accordance with the logic gate relationship. When the probability threshold requirement is reached, the event influencing factors and their influencing relationships are determined to obtain the factor parsing results.

5. The method for intelligent fuel data management based on a data middle platform as claimed in claim 4, characterized in that: When the probability threshold requirement is not met, the method further includes: Obtaining an abnormal event, wherein the abnormal event is an intermediate event or a basic event whose logic gate relationship verification result does not reach a probability threshold; Extracting a historical event record data set based on the abnormal event, performing semantic mining on the historical event record data set, and establishing a factor relationship graph to reflect the semantic association between factors; Based on the factor relationship map, mining explicit factors and latent factors; Fitting the correlation and influence relationship between the dominant factor, the recessive factor and the abnormal event according to the historical event record data set; The associated influence relationship is added to the logic gate relationship, and reverse verification is performed from bottom to top layer by layer based on the event parsing tree until the probability of event occurrence reaches the probability threshold requirement.

6. The method for intelligent fuel data management based on a data middle station as claimed in claim 1, characterized in that: Based on the supply balance impact relationship of the fuel management cycle, the full cycle supply imbalance analysis is performed according to the cycle fuel characteristics to obtain imbalance nodes and imbalance characteristics, including: Set the cycle balance target relationship and penalty conditions of the fuel management cycle; parsing characteristic relationships between fuel management cycles according to the cycle balance target relationship; Constructing an evaluation function according to the characteristic relationship and the penalty condition; Using the evaluation function to evaluate the balance target relationship of the periodic fuel characteristics to obtain a periodic node evaluation value; The imbalance node is located according to the periodic node evaluation value, and the imbalance feature is located in combination with the periodic balance target relationship.

7. The method for intelligent fuel data management based on a data middle station as claimed in claim 6, characterized in that: Also includes: According to the fuel characteristics of the cycle, long-term and short-term supply and demand forecasts are made, and supply timing chain and demand timing chain are established; Based on the connection relationship of the fuel management cycle, the supply timing chain and the demand timing chain are aligned to construct the supply and demand timing chain between the cycle nodes; Predicting the supply-demand balance relationship according to the supply-demand timing chain to obtain a predicted imbalance timing node; Based on the predicted imbalanced timing nodes, timing constraint conditions are analyzed according to the timing distance and the supply timing characteristics of the periodic fuel characteristics to obtain the minimum adjustment time window; The adjustment minimum time window is used as a constraint condition to perform balance compensation on the unbalanced timing nodes.

8. The intelligent fuel data management system based on the data center is characterized by: The system is used to execute the fuel data intelligent management method based on the data middle platform according to any one of claims 1 to 7, including: A management cycle decomposition module, used to decompose the fuel management cycle, analyze the management target of the fuel management cycle, and obtain data factors of the management target; A data acquisition path establishment module, used to establish a data acquisition path according to the data factor, the data acquisition path is associated with the data factor mapping, and the data acquisition path uses the data factor as a data acquisition index, and the data acquisition path is used to establish a connection between the data middle platform and the data source platform; A data update storage module, used to obtain real-time update data of the data source platform through the data acquisition channel, locate the fuel management cycle according to the data factor, and construct a management cycle data block to store in the data center; A cycle characteristic analysis module, used for performing characteristic analysis of the management cycle according to the management cycle data block to obtain cycle fuel characteristics; A supply imbalance analysis module, used to perform a full-cycle supply imbalance analysis based on the supply balance influence relationship of the fuel management cycle and the cycle fuel characteristics to obtain imbalance nodes and imbalance characteristics; The balance compensation module is used to perform balance compensation according to the imbalance nodes and imbalance characteristics to obtain a full-cycle balance management strategy.

Images