An industry chain efficiency tracking method and system based on logistics energy flow coupling

Abstract

The application relates to the technical field of industrial data processing and analysis, and discloses an industry chain efficiency tracking method and system based on logistics energy flow coupling, which comprises the following steps: instantiating key events in an industry chain into entropy weight event elements; linking a plurality of entropy weight event elements into a cause-effect graph; monitoring the information entropy of each data in each entropy weight event element; when the information entropy meets a preset intervention condition, triggering an external system to update data, receiving new data after the corresponding update, and obtaining an optimized cause-effect graph; performing efficiency tracking analysis and / or efficiency deviation attribution analysis to obtain an efficiency analysis result. According to the application, the key events are instantiated into entropy weight event elements containing information entropy, the quantification of the uncertainty of various data sources in the industry chain is realized, the information entropy in the cause-effect graph is monitored, target data updating is realized, the data quality is improved, the efficiency analysis based on the optimized cause-effect graph accurately and quantitatively disassembles the efficiency deviation, and the resolution of the efficiency deviation attribution result is improved.

Description

Technical Field

[0001] This invention relates to the field of industrial data processing and analysis technology, specifically to a supply chain efficiency tracking method and system based on logistics and energy flow coupling. Background Technology

[0002] In modern process industries, such as coal power, chemical, and metallurgical industries, the digitalization and informatization of production processes have reached a high level. The widespread application of various industrial information systems, such as Manufacturing Execution Systems (MES), Distributed Control Systems (DCS), and Laboratory Information Management Systems (LIMS), enables enterprises to collect and store massive amounts of production data throughout the entire industrial chain, including process parameters, material properties, energy consumption indicators, and product quality. Analyzing this data to achieve efficiency optimization, cost control, and quality traceability is a core issue in the current development of intelligent industry.

[0003] However, current systems typically focus solely on the data values ​​themselves when recording data, neglecting the inherent uncertainty. Data from diverse sources—such as precisely calibrated online analytical instrument readings, standardized laboratory test results, routine process sensor measurements, and even manually entered data—exhibits significant differences in reliability and accuracy. Yet, these data are treated equally as deterministic values ​​in the database, causing the inherent differences in data quality to be lost at the very first step of informatization. This neglect of data uncertainty makes any subsequent analysis based on it difficult to guarantee the reliability of its conclusions. When analytical models attempt to establish correlations between these information silos, a mixture of high-quality and low-quality data, the accuracy of the results is greatly reduced because the model cannot distinguish whether a performance deviation is caused by actual process fluctuations or merely by unreliable measurement data. Therefore, when the final output deviates from expectations, accurately and quantitatively tracing and attributing this deviation to a specific upstream link in the supply chain or a specific batch of raw materials becomes extremely difficult. This severely limits a company's ability to conduct refined management and continuous improvement based on data. Summary of the Invention

[0004] This invention provides a supply chain efficiency tracking method and system based on logistics and energy flow coupling, in order to solve the problem that the efficiency deviation in the existing industrial data analysis system is difficult to trace back to the upstream of the supply chain in a precise and quantitative manner due to the neglect of the inherent uncertainty of data sources.

[0005] In a first aspect, the present invention provides a supply chain efficiency tracking method based on logistics and energy flow coupling, the method comprising: Key events are obtained from the target industry chain and instantiated into entropy-weighted event elements. The entropy-weighted event elements include: subject identifier, causal pointer, and information entropy used to characterize the uncertainty of the corresponding data. Based on the subject identifier or causal pointer of the entropy weight event element, multiple entropy weight event elements are linked into a causal graph; Based on the monitoring of the information entropy of each data in each entropy weight event element by the causal graph, when the information entropy meets the preset intervention conditions, the external system is triggered to update the data and receive the corresponding updated new data until the information entropy of each data in each entropy weight event element no longer meets the preset intervention conditions, thus obtaining the optimized causal graph. Based on the optimized causal graph, performance tracking analysis and / or performance deviation attribution analysis are performed to obtain performance tracking results and / or performance deviation attribution results.

[0006] The supply chain efficiency tracking method based on logistics and energy flow coupling provided by this invention quantifies the uncertainty of various data sources in the supply chain by instantiating key events into entropy-weighted event elements containing information entropy. By monitoring the information entropy in the causal graph, it achieves targeted data updates, improves data quality, and enhances relevance and timeliness. Based on the efficiency analysis of the optimized causal graph, it accurately and quantitatively decomposes efficiency deviations, improves the resolution and reliability of efficiency deviation attribution results, and enables managers to more accurately locate the root cause of problems.

[0007] In one optional implementation, the entropy-weighted event element further includes: a data payload that instantiates the critical event as an entropy-weighted event element, including: Based on key events, determine the entity objects and specific event data, and generate the subject identifier according to the first preset format; Extract the causal relationships between key events and generate causal pointers according to the second preset format; Extract at least one business data point from a key event and generate a data payload containing business data attributes according to a third preset format. The business data attributes include: attribute name, attribute value, and information entropy corresponding to the attribute value.

[0008] The supply chain efficiency tracking method based on logistics and energy flow coupling provided by this invention accurately links event data with entity objects in the supply chain by instantiating key events and using subject identifiers. It establishes the relationship between entropy-weighted event elements using causal pointers, ensuring the certainty of causal relationships and the traceability of data flow. The information entropy of each attribute value quantifies the uncertainty of the data. When processing data, it no longer treats all data as equally reliable, but assigns a calculable and objective uncertainty measure to each data input, thus providing a solid foundation for subsequent accurate analysis and uncertainty propagation calculation.

[0009] In one optional implementation, multiple entropy-weighted event elements are linked into a causal graph based on their subject identifiers or causal pointers, including: Extract the identifier of the preceding event element from the causal pointer of the current entropy weight event element, determine the preceding event element of the current entropy weight event element based on the identifier, and create a directed edge from the preceding event element to the current entropy weight event element. Entropy weight event elements with the same subject identifier are sorted in chronological order according to their timestamps and linked to the same entity object through ordered edges; The entropy weight event elements are linked into a causal graph based on directed and ordered edges.

[0010] The supply chain efficiency tracking method based on logistics and energy flow coupling provided by this invention uses causal graphs to construct business logic, physical flow or temporal relationship between key events, thereby characterizing the state of the supply chain. This is conducive to accurate efficiency analysis of each link in the supply chain, and facilitates subsequent reverse attribution based on efficiency deviations, so as to more accurately locate the root cause of the problem.

[0011] In one alternative implementation, the causal graph includes a causal chain consisting of multiple entropy-weighted event elements. If multiple causal chains starting from different subject identifiers converge to an entropy-weighted event element of a mixed event, then the entropy-weighted event element is considered a mixed event element.

[0012] In one optional implementation, performance tracking analysis is performed based on the optimized causal graph to obtain performance tracking results, including: Based on the attribute names of the upstream causal chain of the hybrid event element, and combined with the preset causal chain weights, the corresponding attribute values ​​are weighted and calculated to obtain the hybrid attribute value. Based on the attribute names of the upstream causal chain of the hybrid event element, the corresponding information entropy is weighted and calculated, and combined with configurable process uncertainty parameters, the hybrid information entropy is determined. The data payload of the hybrid event element is calculated based on the hybrid attribute values ​​and hybrid information entropy corresponding to each attribute, and used as the performance tracking result.

[0013] The supply chain efficiency tracking method based on logistics and energy flow coupling provided by this invention converges multi-entity causal chains to form mixed event elements, calculates mixed attribute values ​​by weighting upstream attribute values ​​with preset weights, and determines mixed information entropy by integrating information entropy weighting results and process uncertainty parameters. This accurately constructs the effective payload of mixed event metadata, quantifies the comprehensive effect of multi-source flow data, and takes into account data uncertainty and inherent process deviations, making the efficiency tracking results more consistent with actual production logic.

[0014] In one optional implementation, performance bias attribution analysis is performed based on an optimized causal graph to obtain performance bias attribution results, including: When the final efficiency of the target industry chain deviates, the hybrid event element is determined by reverse traversal based on the causal pointers in the optimized causal graph. Extract multiple upstream causal chains from the hybrid event element, and determine the contribution ratio of each upstream causal chain based on the preset causal chain weights corresponding to each attribute. Based on the contribution ratio, the performance deviation is decomposed and calculated, traced back to the initial entropy weight event element that caused the performance deviation, and the corresponding key event is identified.

[0015] The present invention provides a supply chain efficiency tracking method based on logistics and energy flow coupling. By leveraging the reverse traversal function of optimized causal graphs, it accurately locates mixed event elements and upstream causal chains. Combined with preset weights, it clarifies the contribution ratio of each chain, realizes the quantitative decomposition of efficiency deviations, solves the problem of ambiguous deviation attribution in traditional analysis, traces back to the initial entropy weight event elements and corresponding key events, accurately locks the root cause of deviations, and provides a clear basis for the rectification of problems in the upstream links of the supply chain by quantifying the contribution of each link, thereby improving the ability of refined management and continuous improvement.

[0016] In one alternative implementation, the method further includes: Using a hierarchical or directed graph layout algorithm, all entropy weight event elements, directed edges, and ordered edges in the causal graph are automatically laid out to form a topological view corresponding to the target industry chain. Based on the information entropy in each entropy weight event element, different visual attributes are configured for the corresponding entropy weight event element.

[0017] The supply chain efficiency tracking method based on logistics and energy flow coupling provided by this invention automatically lays out the causal graph into a topological view that fits the actual supply chain through a hierarchical or directed graph layout algorithm. It intuitively presents the relationship between entropy weight event elements and edges and the data flow path. Based on the information entropy, it configures differentiated visual attributes to quickly distinguish the level of data uncertainty. High-entropy risk nodes are clear at a glance, which reduces the threshold for users to understand complex supply chain data and facilitates real-time monitoring of weak links in data quality, providing intuitive support for intervention decision-making and process optimization.

[0018] Secondly, the present invention provides a supply chain efficiency tracking system based on logistics and energy flow coupling, the system comprising: The event instantiation module is used to obtain key events from the target industry chain and instantiate the key events into entropy-weighted event elements. The entropy-weighted event elements include: subject identifier, causal pointer, and information entropy used to characterize the uncertainty of the corresponding data. The causal graph construction module is used to link multiple entropy-weighted event elements into a causal graph based on the subject identifier or causal pointer of the entropy-weighted event element. The adaptive intervention module is used to monitor the information entropy of each data in each entropy weight event element based on the causal graph. When the information entropy meets the preset intervention conditions, it triggers the external system to update the data and receives the corresponding updated new data until the information entropy of each data in each entropy weight event element no longer meets the preset intervention conditions, thus obtaining the optimized causal graph. The performance analysis module is used to perform performance tracking analysis and / or performance deviation attribution analysis based on the optimized cause-effect graph, and to obtain performance tracking results and / or performance deviation attribution results.

[0019] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the method described in the first aspect or any corresponding embodiment thereof.

[0020] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the method described in the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0021] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0022] Figure 1 This is a schematic diagram of an application scenario according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the first process of the supply chain efficiency tracking method based on logistics and energy flow coupling according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the adaptive intervention process in the supply chain efficiency tracking method based on logistics and energy flow coupling according to an embodiment of the present invention. Figure 4 This is a schematic diagram of the second process of the supply chain efficiency tracking method based on logistics and energy flow coupling according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the entropy weight event metadata structure in the supply chain efficiency tracking method based on logistics and energy flow coupling according to an embodiment of the present invention; Figure 6 This is a simplified schematic diagram of a coal blending and gasification process in the supply chain efficiency tracking method based on logistics and energy flow coupling according to an embodiment of the present invention. Figure 7 This is a schematic diagram of the process of efficiency tracking analysis in the supply chain efficiency tracking method based on logistics and energy flow coupling according to an embodiment of the present invention; Figure 8 This is a flowchart illustrating the attribution analysis of performance deviations in the supply chain performance tracking method based on logistics and energy flow coupling according to an embodiment of the present invention. Figure 9 This is a schematic diagram of the complete workflow in a specific embodiment of the supply chain efficiency tracking method based on logistics and energy flow coupling according to an embodiment of the present invention; Figure 10 This is a structural block diagram of a supply chain efficiency tracking system based on logistics and energy flow coupling according to an embodiment of the present invention; Figure 11 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0025] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0026] As an optional application scenario of this invention, such as Figure 1 As shown, this supply chain efficiency tracking system based on logistics and energy flow coupling may include at least one terminal device and at least one server. Figure 1 The system is illustrated in the example, which includes a computer 101, a mobile terminal 102, and a server 103, and the terminal devices such as the computer 101 and the mobile terminal 102 are connected to the server 103 through a network 110.

[0027] Specifically, the terminal device can be a smartphone, tablet, laptop, PDA, desktop computer, game console, smart TV, smart wearable device, in-vehicle terminal, VR (Virtual Reality) device, AR (Augmented Reality) device, etc. Server 103 can be a standalone physical server, a server cluster, a distributed system, or a cloud server providing cloud services. Network 110 can be a wired or wireless network, examples of which include, but are not limited to, the Internet, corporate intranet, local area network, wide area network, mobile communication network, and combinations thereof.

[0028] This invention provides a supply chain efficiency tracking method based on logistics and energy flow coupling. By instantiating key events into entropy-weighted event elements containing information entropy, the uncertainty of various data sources in the supply chain is quantified. Furthermore, causal graphs are used to trace the source of efficiency deviations, thereby incorporating data uncertainty into efficiency analysis and accurately quantifying efficiency deviations to their upstream root causes in the supply chain.

[0029] According to an embodiment of the present invention, a method for tracking supply chain efficiency based on logistics and energy flow coupling is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0030] This embodiment provides a supply chain efficiency tracking method based on logistics and energy flow coupling, which can be used in the aforementioned computer system. Figure 2 This is a flowchart of a supply chain efficiency tracking method based on logistics and energy flow coupling according to an embodiment of the present invention, as shown below. Figure 2 As shown, the process includes the following steps: Step S201: Obtain key events from the target industry chain and instantiate the key events into entropy weight event elements. The entropy weight event elements include: subject identifier, causal pointer, and information entropy used to characterize the uncertainty of the corresponding data.

[0031] Specifically, it communicates with one or more industry chain data sources through data interfaces to obtain key event data of the target industry chain. Industry chain data sources include, but are not limited to: Distributed Control System (DCS), Laboratory Information Management System (LIMS), Manufacturing Execution System (MES), or Enterprise Resource Planning (ERP), and presents the analysis results or visualization interface to the user through the user terminal.

[0032] This process involves continuously or periodically capturing key events from industry chain data sources, processing these events, and encapsulating them into a structured data unit—the entropy-weighted event element. The entropy-weighted event element is the fundamental data unit for information representation and flow, aiming to encapsulate key events in the industry chain, along with the uncertainty of the corresponding event data, into a unified, computable data structure.

[0033] Each entropy weight event element contains an information entropy value, which is used to quantify the uncertainty of the corresponding data contained in the key event. In addition to the information entropy value, the entropy weight event element also contains a topic identifier used to distinguish different key events and a causal pointer used to characterize the relationship between each entropy weight event element.

[0034] Step S202: Link multiple entropy weight event elements into a causal graph based on the subject identifier or causal pointer of the entropy weight event element.

[0035] Specifically, based on the pre-defined business logic, physical flow, or temporal relationships between entropy weight event elements, these entropy weight event elements are linked together to form a causal graph representing the relationships between logistics, energy flow, and information flow in the industrial chain. This graph is a directed acyclic graph, where the nodes are entropy weight event elements and the edges represent the causal or flow relationships between events.

[0036] Step S203: Based on the causal graph, monitor the information entropy of each data in each entropy weight event element. When the information entropy meets the preset intervention conditions, trigger the external system to update the data and receive the corresponding updated new data until the information entropy of each data in each entropy weight event element no longer meets the preset intervention conditions, and obtain the optimized causal graph.

[0037] Specifically, after the causal graph is constructed or during the update process, the information entropy contained in each entropy weight event element in the causal graph is continuously monitored. When the information entropy of any entropy weight event element meets the preset intervention conditions and the value exceeds a preset entropy threshold, the adaptive intervention engine is triggered to generate and send an intervention command to the external system or user terminal.

[0038] This intervention instruction is used to prompt external systems to verify or supplement data collection. The new data obtained is used to perform a targeted update of the causal graph, and the direct result of this update is to reduce the information entropy exceeding the threshold.

[0039] like Figure 3 The diagram illustrates the adaptive intervention process, a closed-loop control procedure. The input is a causal graph, and the output is an intervention command. Periodically, or after each update of the causal graph, each entropy-weighted event node in the graph is traversed. During traversal, each data attribute contained in the data payload within a node is read, and its entropy value is extracted. This extracted entropy value is then compared with a preset, configurable entropy threshold. To achieve refined management, this entropy threshold is not a globally fixed value but is maintained through an entropy threshold configuration table. This table allows different entropy thresholds to be set for different attribute names. Table 1 shows an example table of different attribute names and their corresponding entropy thresholds.

[0040] Table 1 Example table of entropy thresholds

[0041] When making comparisons, first check if the current data attribute name has a specific threshold; if so, use it; otherwise, use a global default threshold.

[0042] When the entropy value of a certain information element in an entropy-weighted event exceeds its corresponding entropy threshold, the adaptive intervention engine is triggered and immediately generates an intervention instruction. This intervention instruction is a structured data message designed to notify external systems or operators to process the highly uncertain data point. The structure of this instruction may include: Event Element ID: The unique hash value of the entropy weight event element that triggered the intervention.

[0043] Attribute name: The name of the data attribute whose information entropy exceeds the threshold.

[0044] Current entropy value: The specific numerical value of the information entropy exceeding the threshold.

[0045] Command type: A predefined command code, such as VALIDATE (request for manual verification), RE-MEASURE (request for remeasurement), or ESTIMATE-CONFIRM (request for confirmation of the estimation basis).

[0046] Timestamp: The time when the instruction was generated.

[0047] The intervention command is sent out through the system's messaging interface, and the system then enters a waiting state to receive a response to the command. After the external system or personnel execute the command (e.g., resampling and testing the material), they will feed back new, more reliable data.

[0048] After the event instantiation module captures new data as a response, it assigns it an initial information entropy significantly lower than the original value (because its source is targeted verification or retesting), and generates a new entropy-weighted event element. The causal graph construction module then updates the causal graph with this new, low-entropy event element, for example, replacing the original high-entropy node. The complete process consisting of monitoring, thresholding, triggering, response, and updating constitutes a targeted update. Through this mechanism, the system proactively manages and optimizes the reliability of its internal data foundation.

[0049] Step S204: Based on the optimized causal graph, perform performance tracking analysis and / or performance deviation attribution analysis to obtain performance tracking results and / or performance deviation attribution results.

[0050] Specifically, the analysis and computation are performed based on an optimized causal graph with high data reliability, which has been adaptively intervened and updated. The propagation of efficacy and uncertainty is tracked by traversing the causal graph in the forward direction, and / or attribution analysis is performed on performance deviations that have occurred by traversing the graph in the reverse direction. Finally, the efficacy analysis engine generates and outputs efficacy tracking results and / or efficacy deviation attribution results.

[0051] The supply chain efficiency tracking method based on logistics and energy flow coupling provided in this embodiment quantifies the uncertainty of various data sources in the supply chain by instantiating key events into entropy-weighted event elements containing information entropy. By monitoring the information entropy in the causal graph, it achieves targeted data updates, improves data quality, and enhances relevance and timeliness. Based on the efficiency analysis of the optimized causal graph, it accurately and quantitatively decomposes efficiency deviations, improves the resolution and reliability of efficiency deviation attribution results, and enables managers to more accurately locate the root cause of problems.

[0052] In some alternative implementations, the method further includes: Step S205: Using a hierarchical or directed graph layout algorithm, all entropy weight event elements, directed edges, and ordered edges in the causal graph are automatically laid out to form a topological view corresponding to the target industry chain.

[0053] Specifically, causal graph data and performance analysis results are converted into a graphical interface and displayed on the user terminal, intuitively showing the topology of the industry chain, data flow paths, and the distribution of data uncertainty in each link.

[0054] Data visualization can be achieved through a human-computer interaction unit. This unit receives the structural data of the causal graph and the results of performance analysis (including performance tracking results and / or performance deviation attribution results), and renders this data into a graphical user interface for display on the user's terminal. A hierarchical or directed graph layout algorithm is employed to automatically lay out all entropy-weighted event node nodes and directed edges representing the links between entropy-weighted event nodes on a two-dimensional interface, forming a topology view corresponding to the actual process flow of the industry chain.

[0055] Step S206: Configure different visual attributes for the corresponding entropy weight event elements based on the information entropy in each entropy weight event element.

[0056] Specifically, the visualization analysis module can perform state rendering, which maps the information entropy value contained in the data payload of each entropy weight event meta node to one or more visual attributes of that node on the interface.

[0057] In one specific embodiment, the mapping relationship between information entropy values ​​and visual attributes includes node color rendering and node state highlighting.

[0058] Node color rendering: Based on the magnitude of the information entropy, different colors are filled for the corresponding nodes. For example, a color gradient is set to map the range of information entropy from to a preset maximum value as a continuous gradient from green (low uncertainty) to yellow (medium uncertainty) and then to red (high uncertainty).

[0059] Node status highlighting: This retrieves the entropy threshold used by the adaptive intervention engine. When a node's information entropy exceeds its corresponding threshold, in addition to changing its color, an extra visual effect is added, such as a flashing border or a pulsed halo. This design provides users with direct visual cues about which data points triggered the intervention conditions.

[0060] In addition, the visual analytics module provides interactive functionality. When a user's input device (such as a mouse cursor) hovers over any node, an information pop-up window appears, displaying detailed data for that entropy weight event element, including the subject identifier, causal pointer, and all attribute names, attribute values, and information entropy in the data payload. When a user clicks on a node, all downstream paths originating from that node and all upstream paths flowing into it are highlighted, enabling end-to-end visual tracking of specific material or energy flows.

[0061] The supply chain efficiency tracking method based on logistics and energy flow coupling provided in this embodiment automatically lays out the causal graph into a topological view that fits the actual supply chain through a hierarchical or directed graph layout algorithm. It intuitively presents the relationship between entropy weight event elements and edges and the data flow path. Based on the information entropy, it configures differentiated visual attributes to quickly distinguish the level of data uncertainty. High-entropy risk nodes are clear at a glance, which reduces the threshold for users to understand complex supply chain data and facilitates real-time monitoring of weak links in data quality, providing intuitive support for intervention decision-making and process optimization.

[0062] This embodiment provides a supply chain efficiency tracking method based on logistics and energy flow coupling, which can be used in the aforementioned computer system. Figure 4 This is a flowchart of a supply chain efficiency tracking method based on logistics and energy flow coupling according to an embodiment of the present invention, as shown below. Figure 4 As shown, the process includes the following steps: Step S301: Obtain key events from the target industry chain and instantiate the key events into entropy weight event elements. The entropy weight event elements include: subject identifier, causal pointer, and information entropy used to characterize the uncertainty of the corresponding data.

[0063] Specifically, the entropy weight event element also includes: data payload, and step S301 above includes: Step S3011: Determine the entity object and specific event data based on the key events, and generate the subject identifier according to the first preset format.

[0064] Specifically, such as Figure 5 The diagram shows the metadata structure of an entropy weight event. The data structure of the entropy weight event metadata includes a subject identifier, a causal pointer, and a data payload. The data payload includes the attribute name, attribute value, and its corresponding information entropy.

[0065] The subject identifier is used to uniquely and structurally identify the physical or logical entity associated with an entropy weight event element. To achieve accurate traceability and association, the subject identifier can be designed as a composite field, such as containing entity type (e.g., raw material batch, production equipment, product batch) and entity ID (e.g., COAL-2821-01, GASIFIER-UNIT-02, AMMONIA-2822-T101). By using the design of the subject identifier, event data can be accurately linked to specific objects in the industry chain.

[0066] Step S3012: Extract the causal relationships between key events and generate causal pointers according to the second preset format.

[0067] Specifically, causal pointers are used to establish the link between the current entropy weight event element and its immediate predecessor event element. The causal pointer stores the unique hash value or globally unique identifier (GUID) of its predecessor entropy weight event element. This design constructs an immutable chain structure, ensuring the determinism of causal relationships and the traceability of data flow. For the initial event in the supply chain (e.g., raw material entering the factory), its causal pointer can be set to a predefined genesis value or a null value.

[0068] Step S3013: Extract at least one business data of the key event and generate a data payload containing business data attributes according to a third preset format. The business data attributes include: attribute name, attribute value and information entropy corresponding to the attribute value.

[0069] Specifically, the data payload is the core part of the entropy weight event element that carries specific business data. It contains one or more data attributes, and each data attribute is a triple, specifically including the attribute name, the attribute value, and the information entropy corresponding to that attribute value.

[0070] Attribute values ​​are specific measurements or recorded values ​​of key events, and their data types can be numeric, Boolean, or string. Information entropy is a non-negative numerical value used to quantitatively characterize the uncertainty or confidence level of the corresponding attribute value. The higher the information entropy value, the greater the uncertainty of the attribute value; an information entropy of 0 indicates that the data is considered completely certain.

[0071] In one specific embodiment, an entropy-weighted event element instantiated from a key event describing incoming coal detection may include the following: Entity Identifier: {Entity Type: Raw Material Batch, Entity ID: COAL-2821-01} Causal pointer: NULL Data payload: Data attribute a: {Attribute name: Calorific value, Attribute value: 29.3 (MJ / kg), Information entropy: 0.10} Data attribute b: {Attribute name: Sulfur content, Attribute value: 0.55 (%), Information entropy: 0.05} In this embodiment, the information entropy of calorific value is 0.10, while the information entropy of sulfur content is 0.05, indicating that the reliability of sulfur content data is higher than that of calorific value data in this test. This structured design makes the uncertainty of the data part of the data itself, and allows it to propagate and evolve in subsequent analysis and calculations.

[0072] The event instantiation module is the data entry point and preprocessing unit of the system of this invention. Its core function is to receive raw data from industry chain data sources, based on, for example... Figure 5 The defined structure is used to create and populate entropy-weighted event elements.

[0073] The event instantiation module is internally configured with data adapters for different data sources (such as DCS, LIMS, and MES) to parse input data in different formats. When a critical event that conforms to preset rules occurs, such as the generation of a new batch inspection report in LIMS, the event instantiation module captures all relevant data for the event and initiates the instantiation process of the entropy-weighted event element.

[0074] In the instantiation process, values ​​are assigned strictly according to the data structure of the entropy-weighted event element: First, entity information, such as batch number COAL-2821-01, is extracted from the raw data to form the subject identifier; simultaneously, the correlation information between events is parsed. For example, if the current event is that a batch of coal enters the coal mill, the unique hash value of the inbound event element for that batch of coal is found and filled into the causal pointer of this event element; specific business data in the event, such as temperature, pressure, and component content, are extracted and used to fill the data payload. Specifically, each piece of business data (e.g., sulfur content and its value 0.55%) is created as a data attribute, and its value is filled into the attribute value field.

[0075] A key function of the event instantiation module is to set the initial information entropy for each attribute value in the data payload. To achieve this, the event instantiation module internally stores or links to a configurable data source credibility configuration table. This table defines the credibility level of different data sources or data types and their corresponding basic information entropy ranges. Table 2 shows an example of a configurable data source credibility configuration table.

[0076] Table 2. Example of configurable data source trustworthiness configuration

[0077] When the event instantiation module processes new data, it first identifies the source of the data. For example, if the data comes from LIMS, the module queries the configuration table mentioned above to determine its credibility level as 2, and selects a value from the range of 0.05 to 0.15 for the attribute value of the data, filling it into the corresponding information entropy field. This selection process can be to take the median value of the range, or to fine-tune the range based on the metadata of the data itself (such as whether it has been reviewed).

[0078] Through the above process, the event instantiation module ensures that every piece of data entering the system is encapsulated into a uniformly structured entropy-weighted event element, and quantifies and solidifies the uncertainty (information entropy) of the data in the first step of entering the system.

[0079] The supply chain efficiency tracking method based on logistics and energy flow coupling provided in this embodiment accurately links event data with entity objects in the supply chain by instantiating key events and using subject identifiers. It establishes the relationship between entropy-weighted event elements using causal pointers, ensuring the certainty of causal relationships and the traceability of data flow. The information entropy of each attribute value quantifies the uncertainty of the data. When processing data, it no longer treats all data as equally reliable, but assigns a calculable and objective uncertainty measure to each data input, thus providing a solid foundation for subsequent accurate analysis and uncertainty propagation calculation.

[0080] Step S302: Link multiple entropy weight event elements into a causal graph based on the subject identifier or causal pointer of the entropy weight event element.

[0081] Specifically, step S302 includes: Step S3021: Extract the identifier of the preceding event element from the causal pointer of the current entropy weight event element, determine the preceding event element of the current entropy weight event element based on the identifier, and create a directed edge from the preceding event element to the current entropy weight event element.

[0082] Specifically, the causal graph is a dynamic book corner structure. When a new entropy weight event element is generated, a linking operation is performed to add the new entropy weight event element as a new node to the causal graph. The linking operation is mainly performed based on the subject identifier and causal pointer inside the entropy weight event element. There are two linking execution methods depending on the linking basis.

[0083] The first method is based on direct links using causal pointers. It reads the identifier (e.g., a unique hash value) of the preceding event element stored in the causal pointer of the new event element. Then, it searches the existing causal graph for a node (i.e., an entropy-weighted event element) with that unique hash value. Once found, a directed edge is created from the found preceding node to the current new node. This method is primarily used to represent process steps or workflows with a clear sequential order.

[0084] Step S3022: The entropy weight event elements with the same subject identifier are sorted according to their timestamps in chronological order and linked to the same entity object through ordered edges.

[0085] Specifically, the second type is based on subject identifier-based association links. In some cases, there are no direct causal pointers between events, but they act on the same physical or logical entity. The module reads the subject identifier of the new event element and searches the causal graph to see if a node with the same subject identifier already exists. If so, the module can link the new event element to the latest event element with the same subject identifier through ordered edges, based on the timestamp of the event, thereby constructing a complete lifecycle trajectory of an entity in the industry chain.

[0086] Step S3023: Link each entropy weight event element into a causal graph based on directed edges and ordered edges.

[0087] Specifically, the relationships between each entropy weight event element are displayed through directed edges and ordered edges, forming a causal graph.

[0088] The supply chain efficiency tracking method based on logistics and energy flow coupling provided in this embodiment uses causal graphs to construct business logic, physical flow, or temporal relationships between key events, thereby characterizing the state of the supply chain. This facilitates accurate efficiency analysis of each link in the supply chain and makes it easier to perform reverse attribution based on efficiency deviations, thus more accurately locating the root cause of the problem.

[0089] Step S303: Based on the causal graph, monitor the information entropy of each data in each entropy weight event element. When the information entropy meets the preset intervention conditions, trigger the external system to update the data and receive the corresponding updated new data, until the information entropy of each data in each entropy weight event element no longer meets the preset intervention conditions, thus obtaining the optimized causal graph. For details, please refer to [link to relevant documentation]. Figure 2 Step S203 of the illustrated embodiment will not be described again here.

[0090] In some optional implementations, the causal graph includes causal chains consisting of multiple entropy-weighted event elements. If multiple causal chains starting from different subject identifiers converge to an entropy-weighted event element of a mixed event, then the entropy-weighted event element is regarded as a mixed event element.

[0091] Specifically, such as Figure 6 The diagram shown is a simplified schematic of the coal blending and gasification process. The first entropy-weighted event element represents the arrival of raw coal batch A at the plant, and the second entropy-weighted event element represents the arrival of raw coal batch B at the plant. Since these two event elements are the initial events, their causal pointers are empty, and they exist as the initial nodes of the causal graph.

[0092] When the coal blending operation occurs, the event instantiation module generates a third coal blending event element. The causal pointer of this third entropy-weighted event element will contain identifiers pointing to the first and second entropy-weighted event elements. Based on this, the causal graph construction module establishes directed edges from the first entropy-weighted event element to the third coal blending event element, and from the second entropy-weighted event element to the third coal blending event element, forming a convergent structure. The subject identifier of the third coal blending event element will be updated to the new coal blending batch C.

[0093] Subsequently, the gasification operation is instantiated as the fourth entropy weight event element, whose causal pointer points to the third entropy weight event element, and whose subject identifier is consistent with the third coal mixing event element. Based on this, a directed edge is established from the third coal mixing event element to the fourth entropy weight event element.

[0094] By continuously executing the above linking operations, the causal graph construction module ultimately generates and maintains a complete, dynamically updated causal graph. This graph, in the form of a Directed Acyclic Graph (DAG), accurately maps the complex processes of the industry chain, where each node (entropy weight event element) carries business data containing uncertain information (information entropy).

[0095] Step S304: Based on the optimized causal graph, perform performance tracking analysis and / or performance deviation attribution analysis to obtain performance tracking results and / or performance deviation attribution results.

[0096] Specifically, in step S304 above, based on the optimized causal graph, performance tracking analysis is performed to obtain performance tracking results, including: Step S3041: Based on the attribute name of the upstream causal chain of the hybrid event element and combined with the preset causal chain weight, the corresponding attribute value is weighted and calculated to obtain the hybrid attribute value.

[0097] Specifically, the computation path is traversed sequentially from upstream to downstream nodes along the direction defined by the causal pointers in the optimized causal graph. When the computation path encounters a convergence node (i.e., a hybrid event element), the performance analysis engine performs calculations on the data payload of the hybrid event element to determine the attribute values ​​and information entropy of the hybrid entity, such as... Figure 7 The diagram shown is a flowchart of the performance tracking analysis process.

[0098] The attribute values ​​are calculated by weighting the attribute values ​​from all upstream causal chains that flow into the hybrid event element. The calculation follows the formula:

[0099] in, The target attribute value represents the hybrid event element; The total number of causal chains that converge to this node; Representing the The attribute values ​​of the corresponding attributes in each upstream causal chain; Is with the first The physical quantities used for weighting in a causal chain, such as the mass or energy content of the batch of material.

[0100] Step S3042: Based on the attribute names of the upstream causal chain of the hybrid event element, the corresponding information entropy is weighted and calculated, and combined with the configurable process uncertainty parameters, the hybrid information entropy is determined.

[0101] Specifically, the calculation of information entropy, based on the weighted calculation of attribute values, incorporates the uncertainties of each upstream causal chain and accounts for the uncertainties introduced by the mixing process itself. Its calculation follows the formula:

[0102] in, The information entropy corresponding to the target attribute of the hybrid event element 3; Representing the Information entropy of corresponding attributes in each upstream causal chain; The total number of causal chains that converge to this node; Is with the first The physical quantities used for weighting in a causal chain, such as the mass or energy content of the batch of material; It is a configurable process uncertainty parameter, which is a non-negative value, used to quantify the new uncertainties introduced by physical or chemical processes such as mixing and processing.

[0103] Step S3043: Calculate the data payload of the hybrid event element based on the hybrid attribute values ​​and hybrid information entropy corresponding to each attribute, as the performance tracking result.

[0104] The supply chain efficiency tracking method based on logistics and energy flow coupling provided in this embodiment converges multi-entity causal chains to form mixed event elements, calculates mixed attribute values ​​by weighting upstream attribute values ​​with preset weights, and determines mixed information entropy by integrating information entropy weighting results and process uncertainty parameters. This accurately constructs the effective payload of mixed event metadata, quantifies the comprehensive effect of multi-source flow data, and takes into account data uncertainty and inherent process deviations, making the efficiency tracking results more consistent with actual production logic.

[0105] In step S304 above, based on the optimized causal graph, an efficacy deviation attribution analysis is performed to obtain the efficacy deviation attribution results, including: Step S3044: When the final efficiency of the target industrial chain deviates, reverse traversal is performed based on the causal pointers in the optimized causal graph to determine the mixed event element.

[0106] Specifically, when the final output efficiency of the industrial chain (such as product output and energy consumption indicators) deviates from the expected value, an efficiency deviation attribution analysis is triggered. Starting from the entropy-weighted event node representing the final output efficiency, a reverse traversal is performed along the edges of the causal graph, such as... Figure 8 The diagram shown is a flowchart of the performance deviation attribution analysis.

[0107] During the reverse traversal, when a convergence node (i.e., a hybrid event element) is encountered, based on the multiple causal chains that converge to that convergence node (such as...), ... Figure 6 The contribution of the first entropy-weighted event element and the second entropy-weighted event element shown is used to quantitatively decompose the total deviation transmitted here.

[0108] Step S3045: Extract multiple upstream causal chains of the mixed event element, and determine the contribution ratio of each upstream causal chain based on the preset causal chain weights corresponding to each attribute.

[0109] Specifically, the contribution of each upstream causal chain is determined based on the weights used when calculating the attribute value of that node in the forward tracing. Specifically, the contribution of the first... The proportion of each upstream causal chain's contribution to the total bias, and its contribution in the forward weighted calculation. The size is directly proportional to the size.

[0110] Step S3046: Based on the contribution ratio, the performance deviation is decomposed and calculated, traced back to the initial entropy weight event element that caused the performance deviation, and the corresponding key event is determined.

[0111] Specifically, by performing this decomposition calculation at each fork or convergence node, the total performance deviation is ultimately traced and allocated to multiple initial events at the source of the industry chain, and an attribution analysis report is output in the form of structured data. This report clearly lists the root causes of the performance deviation and their quantified contribution ratios.

[0112] The supply chain efficiency tracking method based on logistics and energy flow coupling provided in this embodiment accurately locates mixed event elements and upstream causal chains by leveraging the reverse traversal function of optimized causal graphs. Combined with preset weights, it clarifies the contribution ratio of each chain, realizes the quantitative decomposition of efficiency deviations, solves the problem of ambiguous deviation attribution in traditional analysis, traces back to the initial entropy weight event elements and corresponding key events, accurately locks the root cause of deviations, and provides a clear basis for the rectification of problems in the upstream links of the supply chain by quantifying the contribution of each link, thereby improving the ability of refined management and continuous improvement.

[0113] In one specific embodiment, such as Figure 9 As shown, to further illustrate the complete workflow in practical applications, a simplified scenario from coal input to ammonia synthesis in a coal-fired power generation and chemical industry chain is used as an example. The goal of this embodiment is to track and analyze the materials and efficiency of ammonia synthesis production, with an expected daily output of tons.

[0114] Step 1: Initial Event Instantiation: On a certain day, the system receives two raw coal arrival events. The event instantiation module processes them as follows.

[0115] Batch A entering the factory: from a long-term cooperative supplier, the data source is the LIMS inspection report. The module is instantiated as entropy-weighted event element A, with the subject identifier COAL-A-2821. The attribute value of the heat value in the data payload is 29.5 MJ / kg, and the information entropy is set to 0.10 according to the data source credibility configuration table.

[0116] Batch B arriving at the factory: originates from a new supplier, with the data source being the supplier's quality inspection report, and confirmed by local rapid testing. The module is instantiated as entropy-weighted event element B, with the subject identifier COAL-B-2821 and the attribute value of calorific value being 27.5 MJ / kg. Due to the low reliability of the data source, its information entropy is set to 0.35.

[0117] Step 2: Cause-and-effect graph construction and positive performance tracking: The daily production plan uses 70 tons of batch A coal and 1 ton of batch B coal for mixing.

[0118] A coal mixing event is captured, and the event instantiation module generates an entropy weight event element C.

[0119] The causal graph construction module receives event element C, reads its causal pointer, and links event element C after event elements A and B to form a convergent structure.

[0120] The performance analysis engine is invoked to calculate the heat value and information entropy of event element C.

[0121] Attribute value calculation: MJ / kg.

[0122] Information entropy calculation (setting process uncertainty parameters) (0.02) The attribute values ​​and information entropy of event element C are updated to the above calculation results.

[0123] Step 3: Adaptive Intervention: The mixed coal enters the gasifier for gasification. During operation, a temperature reading uploaded by the DCS experiences frequent, small-range fluctuations.

[0124] The event instantiation module captures this vaporization temperature event and generates an entropy-weighted event element D. Due to data fluctuations, the module sets a relatively high information entropy for its temperature attribute, with a value of 0.40.

[0125] The adaptive intervention engine detected during monitoring that the information entropy of event element D was 0, which exceeded the preset entropy threshold of 0.20 for this attribute.

[0126] The engine immediately generates and issues an intervention command of type VALIDATE, which is directed to the temperature sensor.

[0127] The visual analytics module renders the node corresponding to event element D on the interface by flashing red.

[0128] The operator responded to the instruction and, upon on-site inspection, discovered a loose sensor wiring. After tightening, the data stabilized. The new, stable temperature reading was captured by the system and the spectrum was updated with a new event element with an information entropy of 0.05.

[0129] Step 4: Reverse attribution of efficiency deviation: At the end of the day, the MES system recorded the final synthetic ammonia output as 98 tons, which is -2 tons lower than the expected output.

[0130] The performance analysis engine triggers reverse attribution analysis, starting from the final ammonia synthesis production event element and traversing backward along the causal graph.

[0131] The engine traced a portion of the deviation back to its relation to the calorific value of the material during the gasification stage. At the coal blending event element C, the engine decomposed the deviation based on the weights used in the forward calculation (70% for batch A, % for batch B). Since the calorific value of batch B (27.5 MJ / kg) was lower than that of batch A (29.5 MJ / kg) and the average value after blending, most of the calorific value deviation caused by coal quality was attributed to batch B.

[0132] The engine continued to trace back, attributing another portion of the deviation to temporary temperature fluctuations that occurred during the vaporization process.

[0133] Finally, the performance analysis engine output an attribution report: Total deviation: -2.0 tons. Causes: 1) Insufficient calorific value of raw materials, contributing -1.4 tons (of which, batch B coal accounts for -1.1 tons and batch A coal accounts for -0.3 tons); 2) Temperature fluctuations during the gasification process, contributing -0.6 tons.

[0134] This complete process not only tracks the evolution of efficiency and uncertainty throughout the entire production process, but also provides quantitative and traceable attribution analysis results when deviations occur.

[0135] This embodiment also provides a supply chain efficiency tracking system based on logistics and energy flow coupling. This system is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the system described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0136] This embodiment provides a supply chain efficiency tracking system based on logistics and energy flow coupling, such as... Figure 10 As shown, it includes: The event instantiation module 1001 is used to obtain key events from the target industry chain and instantiate the key events into entropy weight event elements. The entropy weight event elements include: subject identifier, causal pointer and information entropy used to characterize the uncertainty of the corresponding data.

[0137] The causal graph construction module 1002 is used to link multiple entropy weight event elements into a causal graph based on the subject identifier or causal pointer of the entropy weight event element.

[0138] The adaptive intervention module 1003 is used to monitor the information entropy of each data in each entropy weight event element based on the causal graph. When the information entropy meets the preset intervention conditions, it triggers the external system to update the data and receives the corresponding updated new data until the information entropy of each data in each entropy weight event element no longer meets the preset intervention conditions, thus obtaining an optimized causal graph.

[0139] The performance analysis module 1004 is used to perform performance tracking analysis and / or performance deviation attribution analysis based on the optimized causal graph, and to obtain performance tracking results and / or performance deviation attribution results.

[0140] In some alternative implementations, the event instantiation module 1001 includes: The entity identifier determination unit is used to determine the entity object and specific event data based on the key event, and generate the entity identifier according to the first preset format.

[0141] The causal pointer generation unit is used to extract the causal relationship between key events and generate causal pointers according to a second preset format.

[0142] The data payload determination unit is used to extract at least one business data of a key event and generate a data payload containing business data attributes according to a third preset format. The business data attributes include: attribute name, attribute value, and information entropy corresponding to the attribute value.

[0143] In some optional implementations, the causal mapping construction module 1002 includes: The first relation determination unit is used to extract the identifier of the preceding event element from the causal pointer of the current entropy weight event element, determine the preceding event element of the current entropy weight event element based on the identifier, and create a directed edge from the preceding event element to the current entropy weight event element.

[0144] The second relation determination unit is used to sort entropy weight event elements with the same subject identifier according to their timestamps in chronological order, and link them to the same entity object through ordered edges.

[0145] The causal graph linking unit is used to link entropy weight event elements into a causal graph based on directed and ordered edges.

[0146] In some alternative implementations, the performance analysis module 1004 includes: The attribute weighting calculation unit is used to calculate the weighted attribute values ​​based on the attribute names of the upstream causal chain of the hybrid event element and in combination with the preset causal chain weights, so as to obtain the hybrid attribute value.

[0147] The hybrid information entropy calculation unit is used to calculate the weighted information entropy based on the attribute names of the upstream causal chain of the hybrid event element, and to determine the hybrid information entropy by combining configurable process uncertainty parameters.

[0148] The tracking result determination unit is used to calculate the data payload of the hybrid event element based on the hybrid attribute value and hybrid information entropy corresponding to each attribute, as the performance tracking result.

[0149] The reverse traversal unit is used to determine the hybrid event element by performing a reverse traversal based on the causal pointer in the optimized causal graph when the final efficiency of the target industry chain deviates.

[0150] The contribution ratio calculation unit is used to extract multiple upstream causal chains of the mixed event element and determine the contribution ratio of each upstream causal chain based on the preset causal chain weights corresponding to each attribute.

[0151] The deviation tracing unit is used to decompose and calculate the performance deviation based on the contribution ratio, trace back to the initial entropy weight event element that caused the performance deviation, and identify the corresponding key event.

[0152] In some alternative implementations, the supply chain efficiency tracking system based on logistics and energy flow coupling also includes: The visual analysis module is used to automatically lay out all entropy weight event elements, directed edges, and ordered edges in the causal graph using hierarchical or directed graph layout algorithms to form a topological view corresponding to the target industry chain; and to configure different visual attributes for the corresponding entropy weight event elements according to the information entropy in each entropy weight event element.

[0153] The supply chain efficiency tracking system based on logistics and energy flow coupling provided in this invention can execute the supply chain efficiency tracking method based on logistics and energy flow coupling provided in any embodiment of this invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the above modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0154] Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0155] The following is a detailed reference. Figure 11The diagram illustrates a structural schematic suitable for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, a graphics processing unit, etc.) 1101, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1102 or a program loaded from memory 1108 into random access memory (RAM) 1103. The RAM 1103 also stores various programs and data required for the operation of the electronic device. The processor 1101, ROM 1102, and RAM 1103 are interconnected via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0156] Typically, the following devices can be connected to I / O interface 1105: input devices 1106 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 1107 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 1108 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1109. Communication device 1109 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 11 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0157] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 1109, or installed from a memory 1108, or installed from a ROM 1102. When the computer program is executed by the processor 1101, it performs the functions defined in the supply chain efficiency tracking method based on logistics and energy flow coupling of the embodiments of the present invention.

[0158] Figure 11 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0159] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the supply chain efficiency tracking method based on logistics and energy flow coupling shown in the above embodiments is implemented.

[0160] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A supply chain efficiency tracking method based on logistics and energy flow coupling, characterized in that, The method includes: Key events are obtained from the target industry chain, and the key events are instantiated into entropy-weighted event elements. The entropy-weighted event elements include: subject identifier, causal pointer, and information entropy used to characterize the uncertainty of the corresponding data. Based on the subject identifier or causal pointer of the entropy weight event element, multiple entropy weight event elements are linked into a causal graph; Based on the causal graph, monitor the information entropy of each data in each entropy weight event element. When the information entropy meets the preset intervention conditions, trigger the external system to update the data and receive the corresponding updated new data until the information entropy of each data in each entropy weight event element no longer meets the preset intervention conditions, and obtain the optimized causal graph. Based on the optimized causal map, performance tracking analysis and / or performance deviation attribution analysis are performed to obtain performance tracking results and / or performance deviation attribution results.

2. The method according to claim 1, characterized in that, The entropy weight event element further includes: a data payload, which instantiates the key event into an entropy weight event element, including: Based on key events, determine the entity objects and specific event data, and generate the subject identifier according to the first preset format; Extract the causal relationships between key events and generate causal pointers according to the second preset format; Extract at least one business data point from a key event and generate a data payload containing business data attributes according to a third preset format. The business data attributes include: attribute name, attribute value, and information entropy corresponding to the attribute value.

3. The method according to claim 1, characterized in that, Based on the subject identifier or causal pointer of the entropy-weighted event element, multiple entropy-weighted event elements are linked into a causal graph, including: Extract the identifier of the preceding event element from the causal pointer of the current entropy weight event element, determine the preceding event element of the current entropy weight event element based on the identifier, and create a directed edge from the preceding event element to the current entropy weight event element. Entropy weight event elements with the same subject identifier are sorted in chronological order according to their timestamps and linked to the same entity object through ordered edges; Based on the directed edges and the ordered edges, the entropy weight event elements are linked into a causal graph.

4. The method according to claim 1, characterized in that, The causal graph includes a causal chain composed of multiple entropy-weighted event elements. If multiple causal chains starting from different subject identifiers converge to an entropy-weighted event element of a mixed event, then the entropy-weighted event element is regarded as a mixed event element.

5. The method according to claim 4, characterized in that, Based on the optimized causal graph, performance tracking analysis is performed to obtain performance tracking results, including: Based on the attribute names of the upstream causal chain of the hybrid event element, and combined with the preset causal chain weights, the corresponding attribute values ​​are weighted and calculated to obtain the hybrid attribute value. Based on the attribute names of the upstream causal chain of the hybrid event element, the corresponding information entropy is weighted and calculated, and combined with configurable process uncertainty parameters, the hybrid information entropy is determined. The data payload of the hybrid event element is calculated based on the hybrid attribute values ​​and hybrid information entropy corresponding to each attribute, and is used as the performance tracking result.

6. The method according to claim 4, characterized in that, Based on the optimized causal map, an efficacy bias attribution analysis is performed to obtain the efficacy bias attribution results, including: When the final efficiency of the target industrial chain deviates, a reverse traversal is performed based on the causal pointers in the optimized causal graph to determine the hybrid event element; Extract multiple upstream causal chains of the hybrid event element, and determine the contribution ratio of each upstream causal chain based on the preset causal chain weights corresponding to each attribute; Based on the contribution ratio, the performance deviation is decomposed and calculated, traced back to the initial entropy weight event element that caused the performance deviation, and the corresponding key event is determined.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: Using a hierarchical or directed graph layout algorithm, all entropy weight event elements, directed edges, and ordered edges in the causal graph are automatically laid out to form a topological view corresponding to the target industry chain. Based on the information entropy in each entropy weight event element, different visual attributes are configured for the corresponding entropy weight event element.

8. A supply chain efficiency tracking system based on logistics and energy flow coupling, characterized in that, The system includes: The event instantiation module is used to obtain key events from the target industry chain and instantiate the key events into entropy weight event elements. The entropy weight event elements include: subject identifier, causal pointer and information entropy used to characterize the uncertainty of the corresponding data. The causal graph construction module is used to link multiple entropy weight event elements into a causal graph based on the subject identifier or causal pointer of the entropy weight event element. An adaptive intervention module is used to monitor the information entropy of each data in each entropy weight event element based on the causal graph. When the information entropy meets the preset intervention conditions, it triggers the external system to update the data and receives the corresponding updated new data until the information entropy of each data in each entropy weight event element no longer meets the preset intervention conditions, thus obtaining an optimized causal graph. The performance analysis module is used to perform performance tracking analysis and / or performance deviation attribution analysis based on the optimized causal map, and to obtain performance tracking results and / or performance deviation attribution results.

9. An electronic device, characterized in that, include: A memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, the processor executing the computer instructions to perform the method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the method of any one of claims 1 to 7.

Images