Knowledge graph-based industrial chain power consumption behavior evaluation method and system

Through knowledge graph and GIS technology, combined with path inference algorithms, the core characteristics of electricity consumption behavior of the industrial chain are identified and evaluated, and the comprehensiveness and accuracy of electricity consumption analysis of complex industrial chains in the existing technology is solved, providing a comprehensive and comprehensive use Electric behavior assessment and optimization recommendations.

CN119089990APending Publication Date: 2024-12-06YUNNAN POWER GRID CO LTD
View PDF 0 Cites 8 Cited by

Patent Information

Application Number
CN202410979796.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-22
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing technology is ineffective in revealing the internal connections between various links in a complex industrial chain, the dynamic changes in power consumption patterns and the driving factors behind it. The feature extraction process relies on manual rules or simple statistical models, resulting in a comprehensive analysis result. Sex and accuracy are limited.

Method used

Using a knowledge graph-based method, by collecting and integrating full-link power monitoring data of the industrial chain, combining GIS technology and path inference algorithms, a spatiotemporal knowledge graph is constructed, and the core features directly related to electricity consumption behavior are identified, and the feature structure is constructed. Methods comprehensive scores were performed.

Benefits of technology

A comprehensive and multi-level assessment of electricity consumption behavior in the industrial chain has been achieved, complex relationship paths have been revealed, comprehensive and accurate analysis has been improved, and scientific basis and decision-making support for energy management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119089990A_ABST
    Figure CN119089990A_ABST
Patent Text Reader

Abstract

The invention discloses an industrial chain power consumption behavior evaluation method and system based on a knowledge graph, and relates to the technical field of industrial chain power consumption feature extraction, and the method comprises the steps: collecting full-link power monitoring data of an industrial chain, integrating third-party data, and storing the preprocessed data in a database; geographic position information is integrated by using a GIS technology, spatio-temporal data are visually displayed on a map, and preliminary feature extraction and visual analysis are carried out; entity and relation information is defined, and a space-time knowledge graph is constructed; a path reasoning algorithm is adopted to search for a relation path between the features in the space-time knowledge graph, an optimal relation path between the features is obtained, and core features directly associated with the power consumption behaviors are recognized; and calculating a comprehensive score of the core features of the power consumption behavior by applying a feature construction method, and evaluating the industrial chain power consumption behavior. According to the invention, through integration of multi-source data, space-time visualization analysis, knowledge graph construction and comprehensive score evaluation, comprehensive and multi-level evaluation of industry chain power consumption behaviors is realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of industrial chain electricity consumption feature extraction, and in particular to an industrial chain electricity consumption behavior evaluation method and system based on knowledge graph. Background Art

[0002] In the current era of parallel development of informatization and intelligence, data-driven decision support systems have become one of the core competitiveness of many industries, especially in the field of energy management. Efficient and accurate analysis of electricity consumption behavior has immeasurable value in promoting energy conservation and emission reduction and optimizing resource allocation. In recent years, with the rapid development of big data technology and the continuous maturity of artificial intelligence algorithms, knowledge graphs, as a structured form of knowledge representation, have shown great potential in integrating multi-source heterogeneous data and mining deep related information, and have gradually become a key technical means to improve data analysis capabilities.

[0003] In the field of electricity consumption management in the industrial chain, traditional methods usually rely on single-dimensional statistical analysis of electricity consumption data, such as daily electricity consumption records, load curve depiction, etc. Although these methods can provide a basic overview of electricity consumption, they are unable to reveal the internal connections between various links in the complex industrial chain, the dynamic changes in electricity consumption patterns and the driving factors behind them. In addition, the lack of consideration of geographic spatial dimensions makes it difficult for existing analyses to accurately grasp the impact of geographic location on electricity consumption behavior, especially in scenarios where distributed energy systems and regional electricity consumption differences are significant. This limitation is more prominent. At the same time, in the process of feature extraction, most existing technologies rely on manually set rules or simple statistical models, lacking the exploration and understanding of the deep laws of electricity consumption behavior, resulting in limited comprehensiveness and accuracy of the analysis results. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an industrial chain electricity consumption behavior evaluation method and system based on knowledge graph to solve the problem that traditional methods are incapable of revealing the internal connections between various links in a complex industrial chain, the dynamic changes in electricity consumption patterns and the driving factors behind them. In the process of feature extraction, the existing technologies mostly rely on manually set rules or simple statistical models, lack the exploration and understanding of the deep-seated laws of electricity consumption behavior, resulting in limited comprehensiveness and accuracy of the analysis results.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] The embodiment of the present invention provides a method for evaluating electricity consumption behavior of an industrial chain based on a knowledge graph, which includes collecting full-link power monitoring data of the industrial chain, integrating third-party data, and storing the pre-processed data in a database;

[0008] Use GIS technology to integrate geographic location information and visually display spatiotemporal data on maps to perform preliminary feature extraction and visualization analysis;

[0009] Based on the analysis results, define entity and relationship information and build a spatiotemporal knowledge graph;

[0010] A path reasoning algorithm is used to find the relationship path between features in the spatiotemporal knowledge graph, obtain the optimal relationship path between features, and identify the core features directly related to electricity consumption behavior;

[0011] The feature construction method is applied to calculate the comprehensive score of the core characteristics of electricity consumption behavior and evaluate the electricity consumption behavior of the industrial chain.

[0012] As a preferred solution of the knowledge graph-based industrial chain electricity consumption behavior assessment method described in the present invention, the collection of full-link electricity monitoring data of the industrial chain and the integration of third-party data include selecting suitable IoT sensor types according to the structural characteristics of the industrial chain to ensure coverage of electricity usage in the entire link, formulating a detailed deployment plan, physically installing the sensors according to the deployment plan, configuring network connections, completing the stable transmission of data from the sensors to the database, integrating third-party data, establishing an API interface with meteorological service providers and public holiday databases, and automatically obtaining meteorological data and holiday information at a regular interval and synchronizing them to the database.

[0013] As a preferred solution of the method for evaluating electricity consumption behavior of an industrial chain based on knowledge graph described in the present invention, a data receiving port is set in the database, and the format of the received raw data is checked and standardized to ensure that all data follow a unified data model, and data cleaning processing is implemented.

[0014] As a preferred solution of the method for evaluating electricity consumption behavior of the industrial chain based on knowledge graph described in the present invention, the method of integrating geographic location information using GIS technology and visually displaying spatiotemporal data on a map to perform preliminary feature extraction and visualization analysis includes the following steps:

[0015] Use GIS technology to match and calibrate the geographic location information collected by the sensor with the physical coordinates of the monitoring point to ensure the accuracy of the geographic location data;

[0016] Use GIS tools to create spatiotemporal data layers, define time series animations, and overlay meteorological data and holiday markers to map spatiotemporal data onto two-dimensional or three-dimensional maps to achieve an intuitive display of electricity consumption status;

[0017] On the map interface, through heat maps and trajectory analysis methods, the electricity consumption characteristics of hot spots, peak electricity consumption periods and weather-related electricity consumption patterns are preliminarily extracted, and a visual analysis of electricity consumption distribution overview, time series trends and correlation analysis with third-party data is conducted.

[0018] As a preferred solution of the method for evaluating electricity consumption behavior of an industrial chain based on a knowledge graph according to the present invention, the construction of the knowledge graph includes the following steps:

[0019] Determine the core entities of the knowledge graph, including enterprises, devices, geographic locations, and timestamps;

[0020] Define entity relationship information and convert it into the triple data required for the knowledge graph, including the enterprise to which the equipment belongs, the geographical location of the equipment, and the changes in power consumption status over time;

[0021] Use the graph database to import triple data, build an initial static knowledge graph, and design attribute labels for each entity and relationship;

[0022] Deploy a real-time data stream processing framework to receive real-time monitoring data and third-party data from IoT sensors. The data stream is decoded and formatted and converted into graph update instructions.

[0023] When a change in power consumption status or an update in geographic location is detected, the update of graph nodes or edges is triggered. Each update operation includes adding, modifying or deleting nodes and edges in the graph. At the same time, the time series nodes are maintained to record the historical trajectory of status changes.

[0024] New entities are introduced into the map, including power consumption trend areas and those affected by geographic location. Power consumption trend areas predict the future power consumption trend of the equipment based on the power consumption data of each device, and the prediction results are added as new map attributes. The influence of geographic location uses GIS tools to analyze the impact of geographic location characteristics on power consumption patterns.

[0025] As a preferred solution of the method for evaluating electricity consumption behavior of an industrial chain based on a knowledge graph according to the present invention, the method of finding the relationship path between features in the spatiotemporal knowledge graph using a path reasoning algorithm includes the following steps:

[0026] Define the logical connections between entities and relations in the spatiotemporal knowledge graph;

[0027] Define the use of a graphical interface to display feature relationship paths, where nodes represent features, edges represent relationships, edge width reflects the strength of the relationship, and edge color reflects the nature of the relationship;

[0028] Find the target feature of the relationship path, set it as the end node, select one or more features as the starting node, start the search, and each time the node is expanded, select the next exploration node based on the actual cost from the starting node to the current node and the shortest path length from the current node to the target node;

[0029] Sort all valid paths found, and prioritize those with shorter path lengths, higher rule matching, and more logically direct paths;

[0030] Identify the core features directly related to electricity usage behavior, analyze the nodes and edges on the optimal path, and map them to the features related to specific electricity usage behavior.

[0031] As a preferred solution of the method for evaluating electricity consumption behavior of an industrial chain based on knowledge graph described in the present invention, the application feature construction method calculates the comprehensive score of the core features of electricity consumption behavior, and the evaluation of electricity consumption behavior of the industrial chain includes the following steps:

[0032] Define basic time series features and user attribute features. Basic time series features include daily electricity consumption D daily , Peak power consumption time T peak and load curve slope S slope , user attribute characteristics include industry category code C industry and geographic location code D location ;

[0033] Construct composite features, power consumption change rate CR change , Load Peak-to-Valley Ratio PVR peak-valley and seasonal index SI seasonal ;

[0034] Set scoring indicators to quantify the strength of association between characteristics and electricity consumption behavior;

[0035] The comprehensive score of the core characteristics of electricity consumption behavior is expressed as:

[0036]

[0037]

[0038] Among them, γ is the parameter of the control function steepness; Ω is the environmental influence function, Λ weather is the actual impact intensity of meteorological conditions, Λ weather-max is the greatest impact intensity of meteorological conditions in history, Λ holiday is the actual impact intensity of holidays, Λ holiday-max is the maximum impact intensity of holidays in history, β1 and β2 are adjustment coefficients; is a composite eigenvector The weighted combination function reflects the comprehensive contribution of different features to the comprehensive score. is the normalized value of the ith feature, ω i is a weight vector, indicating the importance of the i-th feature in the comprehensive score, and n is the total number of features; is the daily power consumption D daily After normalization, the value is the peak power consumption time T peak After normalization, the value is the load curve slope S slope After normalization, the value Industry category code C industry After normalization, the value is the geographic location code D location After normalization, the value is the rate of change of power consumption CR change After normalization, the value is the load peak-to-valley ratio PVR peak-valley After normalization, the value is the seasonal index SI seasonal The normalized value;

[0039] Based on the comprehensive scoring results, analyze the industry chain for high electricity efficiency, large optimization space, or abnormal electricity usage behaviors;

[0040] When S = 0, it means that the electricity efficiency is extremely low and there are serious problems with electricity usage in the industrial chain;

[0041] When S < 0.5, it means that the electricity efficiency is low and there are specific problem areas in the electricity consumption behavior in the industrial chain;

[0042] When S>0.7, it means that although the electricity efficiency is good, there is still room for fine-tuning the electricity consumption behavior in the industrial chain;

[0043] When S=1, it means that the electricity consumption efficiency is extremely high and the electricity consumption behavior in the industrial chain is in efficient operation.

[0044] In the second aspect, the present invention provides an industrial chain electricity consumption behavior evaluation system based on knowledge graph, including a data collection module, a visualization analysis module, a spatiotemporal knowledge graph construction module, an optimal path search module, and an industrial chain electricity consumption evaluation module;

[0045] The data collection module is used to collect the full-link power monitoring data of the industrial chain, integrate third-party data, and store the pre-processed data in the database;

[0046] The visualization analysis module is used to integrate geographic location information using GIS technology, and to visually display spatiotemporal data on a map, and to perform preliminary feature extraction and visualization analysis;

[0047] The spatiotemporal knowledge graph construction module is used to define entity and relationship information based on the analysis results and construct a spatiotemporal knowledge graph;

[0048] The optimal path finding module is used to find the relationship path between features in the spatiotemporal knowledge graph using a path reasoning algorithm, obtain the optimal relationship path between features, and identify the core features directly related to the electricity consumption behavior;

[0049] The module for evaluating electricity consumption in the industrial chain is used to apply a feature construction method, calculate a comprehensive score of the core features of electricity consumption behavior, and evaluate the electricity consumption behavior of the industrial chain.

[0050] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the method for evaluating electricity consumption behavior of an industrial chain based on a knowledge graph as described in the first aspect of the present invention is implemented.

[0051] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the method for evaluating electricity consumption behavior of an industrial chain based on a knowledge graph as described in the first aspect of the present invention.

[0052] The beneficial effects of the present invention are as follows: the present invention deeply integrates the full-link power monitoring data of the industrial chain with third-party data (such as meteorological information, economic indicators, etc.), and uses geographic information system (GIS) technology to achieve spatial dimension integration and visualization of data, thereby laying a solid foundation for the spatiotemporal characteristic analysis of electricity consumption behavior. By defining entities and relationships under the knowledge graph framework, it is possible to not only capture the direct connection between electricity consumption data, but also reveal the complex relationship paths hidden behind the data through path reasoning algorithms, and identify the core features that directly affect electricity consumption behavior. Furthermore, through innovative feature construction methods, these core features are comprehensively scored, achieving a comprehensive and multi-level evaluation of the electricity consumption behavior of the industrial chain, providing a scientific basis and decision-making support for optimizing energy utilization and improving energy efficiency management. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0054] Figure 1 This is a flow chart of the method for evaluating electricity consumption behavior of an industrial chain based on a knowledge graph in Example 1.

[0055] Figure 2 This is a flow chart of the knowledge graph-based industrial chain electricity consumption behavior assessment system in Example 1. DETAILED DESCRIPTION

[0056] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0057] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0058] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0059] Example 1

[0060] Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides an industrial chain electricity consumption behavior evaluation method based on a knowledge graph, comprising the following steps:

[0061] S1. Collect the full-link power monitoring data of the industrial chain, integrate third-party data, and store the pre-processed data in the database.

[0062] Furthermore, collecting the full-chain power monitoring data of the industrial chain and integrating third-party data includes the following steps:

[0063] According to the structural characteristics of the industrial chain, select the appropriate type of IoT sensor to ensure that the power usage of the entire chain is covered;

[0064] Develop a detailed deployment plan, including the sensor type, quantity, installation location and communication protocol for each monitoring point to ensure that the data is comprehensive and without omissions;

[0065] Physically install sensors according to the deployment plan and configure network connections to ensure that sensors can stably transmit data to the database;

[0066] Integrate third-party data, establish API interfaces with meteorological service providers and public holiday databases, automatically obtain meteorological data and holiday information at regular intervals, and synchronize them to the database.

[0067] It should be noted that a data receiving port is set up in the database to perform format checking and standardization conversion on the received raw data to ensure that all data follows a unified data model and implement data cleaning processing.

[0068] It should also be noted that through this step, comprehensive coverage of electricity usage in the industrial chain is achieved, including not only direct electricity monitoring data, but also supplementary information from third parties, such as environmental data, market dynamics, etc. Such a data integration strategy greatly enriches the basis for analysis and lays a diversified data foundation for subsequent in-depth mining. The data is stored in the database after preprocessing, which ensures the standardization, integrity and accessibility of the data, and facilitates efficient retrieval and analysis. It provides a unified and powerful data platform for energy consumption monitoring and management of the industrial chain, improves the efficiency and quality of data processing, and creates conditions for subsequent intelligent analysis.

[0069] S2. Use GIS technology to integrate geographic location information and visually display spatiotemporal data on maps to perform preliminary feature extraction and visualization analysis.

[0070] Furthermore, GIS technology is used to integrate geographic location information and visually display spatiotemporal data on a map. Preliminary feature extraction and visualization analysis include the following steps:

[0071] Use GIS technology to match and calibrate the geographic location information collected by the sensor with the physical coordinates of the monitoring point to ensure the accuracy of the geographic location data;

[0072] Use GIS tools to create spatiotemporal data layers, define time series animations, and overlay meteorological data and holiday markers to map spatiotemporal data onto two-dimensional or three-dimensional maps to achieve an intuitive display of electricity consumption status;

[0073] On the map interface, through heat maps and trajectory analysis methods, the electricity consumption characteristics of hot spots, peak electricity consumption periods and weather-related electricity consumption patterns are preliminarily extracted, and a visual analysis of electricity consumption distribution overview, time series trends and correlation analysis with third-party data is conducted.

[0074] It should be noted that for mobile devices or temporarily deployed sensors, GPS tracking and geocoding technologies are used for positioning integration.

[0075] It should also be noted that this step, through the application of GIS technology, closely combines power data with geographic location information, making the presentation of spatiotemporal data more intuitive and easy to understand. Visualization on the map can not only quickly identify power consumption patterns and trends in different geographic locations, but also reveal the impact of spatial distribution on power consumption behavior. Preliminary feature extraction and visual analysis help to quickly identify anomalies and patterns, paving the way for in-depth research on the power consumption characteristics of specific areas or links. It improves the intuitiveness and efficiency of data interpretation, making it easier for decision makers to quickly grasp the overall power consumption situation and discover potential regional problems or opportunities.

[0076] S3. Based on the analysis results, define entity and relationship information and build a spatiotemporal knowledge graph.

[0077] Furthermore, building a knowledge graph includes the following steps:

[0078] Determine the core entities of the knowledge graph, including enterprises, devices, geographic locations, and timestamps;

[0079] Define entity relationship information and convert it into the triple data required for the knowledge graph, including the enterprise to which the equipment belongs, the geographical location of the equipment, and the changes in power consumption status over time;

[0080] Use the graph database to import triple data, build an initial static knowledge graph, and design attribute labels for each entity and relationship;

[0081] Deploy a real-time data stream processing framework to receive real-time monitoring data and third-party data from IoT sensors. The data stream is decoded and formatted and converted into graph update instructions.

[0082] When a change in power consumption status or an update in geographic location is detected, the update of graph nodes or edges is triggered. Each update operation includes adding, modifying or deleting nodes and edges in the graph. At the same time, the time series nodes are maintained to record the historical track of status changes. If the current reading of a device exceeds the threshold, the addition of the "device status abnormality" label is triggered.

[0083] New entities are introduced into the map, including power consumption trend areas and those affected by geographic location. Power consumption trend areas predict the future power consumption trend of the equipment based on the power consumption data of each device, and the prediction results are added as new map attributes. The influence of geographic location uses GIS tools to analyze the impact of geographic location characteristics on power consumption patterns.

[0084] It should also be noted that by defining entity and relationship information and constructing a spatiotemporal knowledge graph, this process deepens the level of understanding of electricity consumption behavior. The clear definition of entities and relationships allows complex data relationships to be structured, including not only direct connections between entities, but also evolutionary relationships in time series, forming a highly connected knowledge network. It provides a high-level analysis tool that can reveal the deep logic and causal relationships behind electricity use, providing a solid theoretical foundation for accurate prediction and decision support.

[0085] S4. Use the path reasoning algorithm to find the relationship path between features in the spatiotemporal knowledge graph, obtain the optimal relationship path between features, and identify the core features directly related to electricity consumption behavior.

[0086] Furthermore, the path inference algorithm is used to find the relationship path between features in the spatiotemporal knowledge graph, which includes the following steps:

[0087] Define the logical connections between entities and relations in the spatiotemporal knowledge graph; if entity X has feature Y and Y is associated with Z, then it implies that X indirectly has feature Z;

[0088] Define the use of a graphical interface to display feature relationship paths, where nodes represent features, edges represent relationships, edge width reflects the strength of the relationship, and edge color reflects the nature of the relationship;

[0089] Find the target feature of the relationship path, set it as the end node, select one or more features as the starting node, start the search, and each time the node is expanded, select the next exploration node based on the actual cost from the starting node to the current node and the shortest path length from the current node to the target node;

[0090] Sort all valid paths found, and prioritize those with shorter path lengths, higher rule matching, and more logically direct paths;

[0091] Identify the core features directly related to electricity usage behavior, analyze the nodes and edges on the optimal path, and map them to the features related to specific electricity usage behavior.

[0092] It should also be noted that this step uses the path reasoning algorithm to explore the most relevant paths between features in a complex knowledge graph, which is a key step in digging deeper into electricity consumption behavior patterns. Through algorithm optimization, the core features that have a direct impact on electricity consumption behavior are identified, avoiding the interference of irrelevant factors and focusing on the most influential variables. This greatly improves the accuracy and efficiency of feature selection, allowing subsequent evaluation and optimization measures to be targeted and solve the problem of low electricity efficiency in a targeted manner.

[0093] S5. Apply the feature construction method to calculate the comprehensive score of the core characteristics of electricity consumption behavior and evaluate the electricity consumption behavior of the industrial chain.

[0094] Furthermore, the feature construction method is applied to calculate the comprehensive score of the core features of electricity consumption behavior. The evaluation of the electricity consumption behavior of the industrial chain includes the following steps:

[0095] Define basic time series features and user attribute features. Basic time series features include daily electricity consumption D daily , Peak power consumption time T peak and load curve slope S slope , user attribute characteristics include industry category code C industry and geographic location code D location ;

[0096] Construct composite features, power consumption change rate CR change , Load Peak-to-Valley Ratio PVR peak-valley and seasonal index SI seasonal ;

[0097] Set scoring indicators to quantify the strength of association between characteristics and electricity consumption behavior;

[0098] The comprehensive score of the core characteristics of electricity consumption behavior is expressed as:

[0099]

[0100]

[0101]

[0102]

[0103] Among them, γ is the parameter of the control function steepness; Ω is the environmental influence function, Λ weather is the actual impact intensity of meteorological conditions, Λ weather-max is the greatest impact intensity of meteorological conditions in history, Λ holiday is the actual impact intensity of holidays, Λ holiday-max is the maximum impact intensity of holidays in history, β1 and β2 are adjustment coefficients; is a composite eigenvector The weighted combination function reflects the comprehensive contribution of different features to the comprehensive score. is the normalized value of the ith feature, ω i is a weight vector, indicating the importance of the i-th feature in the comprehensive score, and n is the total number of features; is the daily power consumption D daily After normalization, the value is the peak power consumption time T peak After normalization, the value is the load curve slope S slope After normalization, the value Industry category code C industry After normalization, the value is the geographic location code D location After normalization, the value is the rate of change of power consumption CR change After normalization, the value is the load peak-to-valley ratio PVR peak-valley After normalization, the value is the seasonal index SI seasonal The normalized value;

[0104] The expression of the power consumption change rate is:

[0105]

[0106] The expression of load peak-to-valley ratio is:

[0107]

[0108] in, is the average electricity usage time during non-peak hours;

[0109] The expression of seasonal index is:

[0110]

[0111] Among them, D monthly,m is the average monthly electricity consumption, is the annual average electricity consumption;

[0112] Based on the comprehensive scoring results, analyze the industry chain for high electricity efficiency, large optimization space, or abnormal electricity usage behaviors;

[0113] When S=0, it means that the electricity efficiency is extremely low and there are serious problems with electricity usage in the industrial chain; there may be serious energy waste, chaotic management or serious problems in the system, and no effective energy-saving measures have been taken.

[0114] When S < 0.5, it means that the electricity efficiency is low and there are specific problem areas in the electricity usage behavior in the industrial chain; equipment aging, poor management, improper management during peak hours or lack of energy-saving measures, etc., require in-depth analysis.

[0115] When S>0.7, it means that although the electricity efficiency is good, there is still room for fine-tuning of electricity usage behavior in the industrial chain; such as subtle application of energy-saving technologies or more flexible electricity usage strategies.

[0116] When S=1, it means that the electricity consumption efficiency is extremely high, and the electricity consumption behavior in the industrial chain is in efficient operation; the system is properly managed, energy is fully utilized, energy-saving measures are in place, and there is almost no waste, which reflects the best practice.

[0117] It should be noted that the S value, as a comprehensive score of electricity consumption behavior, is an important indicator used to quantitatively evaluate electricity consumption efficiency, rationality and optimization potential. Its size directly reflects the degree of optimization and efficiency level of electricity consumption behavior. Specifically, the relationship between the S value and electricity consumption behavior can be explained in the following aspects:

[0118] Generally speaking, the higher the S value, the more optimized the electricity use behavior, that is, the higher the electricity use efficiency and the more reasonable the energy use, indicating good energy management practices and the implementation of energy conservation and emission reduction measures. On the contrary, a lower S value indicates that there is waste in electricity use behavior, or it is inefficient, and there may be room for improvement.

[0119] The S value not only reflects the current electricity consumption status, but also reveals the dynamics of electricity consumption behavior through its changing trend. If S increases over time, it means that electricity consumption behavior is improving towards a more efficient and environmentally friendly direction, and the optimization measures are effective; if it decreases, it may be that adverse changes or management omissions have occurred, indicating that immediate measures need to be taken to correct them.

[0120] The S value can also reflect the impact of environmental factors (such as weather and holidays) on electricity consumption behavior and the effectiveness of adjustment strategies. For example, if the S value remains high under severe weather conditions, it means that the emergency plan is appropriate; if the holiday management is proper, the S value fluctuates little, reflecting that the dispatch strategy is effective and the dispatch arrangement is reasonable.

[0121] As a dynamic indicator, regular evaluation of Score changes can monitor the improvement or degradation of electricity consumption behavior over time and provide data support for long-term strategic adjustments.

[0122] By comparing the S values ​​of different links or periods, we can quickly identify abnormal or inefficient links in electricity consumption behavior and provide a basis for optimization measures. For example, if the S value of a certain area is much lower than the average, it may indicate that the equipment in that area is aging or improperly managed, and it needs to be inspected and upgraded.

[0123] As a comprehensive score of electricity consumption behavior, it is a quantitative tool for evaluating electricity efficiency, identifying problems, guiding strategy optimization, and evaluating progress. Its size directly reflects the degree of optimization of behavior, is closely linked to efficiency and management quality, and is a direct reflection of energy management effectiveness. It provides customized energy-saving suggestions and optimization strategies for different entities in the industrial chain.

[0124] It should also be noted that the comprehensive scoring of core features through feature construction methods is an important part of the quantitative evaluation of the entire electricity consumption behavior pattern. This process not only takes into account the importance of individual features, but also takes into account the interaction between features, forming an evaluation system that comprehensively reflects the health of electricity consumption behavior. It provides a quantitative evaluation standard for the electricity consumption efficiency of the industrial chain, enabling managers to clearly understand the gap between the current state and the ideal state, and then guide the rational allocation of resources and strategy adjustments, and promote the development of the industrial chain in a more efficient and sustainable direction.

[0125] The present embodiment also provides an industrial chain electricity consumption behavior evaluation system based on a knowledge graph, including a data collection module, a visualization analysis module, a spatiotemporal knowledge graph construction module, an optimal path search module, and an industrial chain electricity consumption evaluation module; the data collection module is used to collect the full-link power monitoring data of the industrial chain, integrate third-party data, and store the pre-processed data in a database; the visualization analysis module is used to integrate geographic location information using GIS technology, and intuitively display spatiotemporal data on a map, perform preliminary feature extraction and visualization analysis; the spatiotemporal knowledge graph construction module is used to define entity and relationship information based on the analysis results, and construct a spatiotemporal knowledge graph; the optimal path search module is used to use a path reasoning algorithm to find the relationship path between features in the spatiotemporal knowledge graph, obtain the optimal relationship path between features, and identify the core features directly related to electricity consumption behavior; the industrial chain electricity consumption evaluation module is used to apply a feature construction method, calculate the comprehensive score of the core features of electricity consumption behavior, and evaluate the electricity consumption behavior of the industrial chain.

[0126] This embodiment also provides a computer device, which is suitable for the case of an industrial chain electricity consumption behavior assessment method based on a knowledge graph, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the file encryption method proposed in the above embodiment.

[0127] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0128] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for evaluating electricity consumption behavior of an industrial chain based on a knowledge graph as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a disk or an optical disk.

[0129] In summary, the present invention not only makes up for the shortcomings of the existing technology in multi-dimensional data integration, visualization analysis of spatiotemporal characteristics, deep relationship mining, and comprehensive evaluation of electricity consumption behavior, but also provides a powerful tool for refined management and intelligent decision-making of the industrial chain, and is expected to play an important role in promoting the construction of energy Internet and promoting green and low-carbon transformation.

[0130] Example 2

[0131] Referring to Table 1 and Table 2, which is the second embodiment of the present invention, in order to further verify the advancement of the present invention, experimental simulation data of the industrial chain electricity consumption behavior evaluation method based on the knowledge graph are provided.

[0132] This example selects a typical manufacturing supply chain as the research object, covering raw material supply, manufacturing plants, logistics distribution and terminal sales.

[0133] First, based on the characteristics of the industrial chain structure, IoT devices including smart meters, temperature and humidity sensors, and motion sensors were selected to ensure full-link power and environmental data monitoring. The deployment plan carefully planned 200 monitoring points, each of which was equipped with 2 to 4 sensors, using the LoRaWAN protocol to ensure long-range low-power transmission. At the same time, it was integrated with the National Meteorological Administration and the holiday database API interface to automatically update meteorological data and holiday tags every hour, and all data was stored in the MongoDB database after format verification and standardization.

[0134] Secondly, ArcGIS software was used to accurately match sensor locations with physical coordinates, creating a spatiotemporal data layer containing electricity usage. Through time series animation, temperature, humidity and holiday information were superimposed to intuitively reflect the trend of electricity consumption. Heat maps and trajectory analysis revealed the strong correlation between high energy consumption areas, peak electricity consumption periods (19:00-21:00) and high temperature weather, as well as changes in electricity consumption patterns during holidays.

[0135] Then, based on the analysis, we identified enterprises, devices, geographic locations, and timestamps as core entities, and defined triple data of device ownership, geographic location relationships, and time series changes. We built an initial knowledge graph using the Neo4j graph database, and developed a real-time data stream processing framework to automatically update the graph and record the history of power consumption status changes. In addition, we predicted future power consumption trends through machine learning models, and added new entities such as "power consumption trend area" and "affected by geographic location" to the graph.

[0136] Finally, the Dijkstra algorithm was used to find the shortest path between features in the knowledge graph and define the logical connection between nodes and edges. Through the interface display, the core feature paths directly related to "high temperature weather" and "peak power consumption time", "equipment aging" and "load curve slope increase" were identified, revealing the deep logic of power consumption behavior.

[0137] The comprehensive score is calculated as shown in the following table:

[0138] Table 1 Experimental data table

[0139] Experimental subjects Raw material suppliers Manufacturing Plant Logistics and distribution Terminal Sales Timestamp 2023-04-01 2023-04-01 2023-04-01 2023-04-01 Daily electricity consumption (kWh) 3500 15000 2500 500 Peak power consumption time (h) 18 20 15 10 Load curve slope (%) 2 3 1 1 Industry Category Code -1 2 5 4 Geolocation Code 501 502 503 504 Electricity consumption change rate 1.2 1.4 1.1 1 Load peak-to-valley ratio 2.1 2.5 2.2 1.9 Seasonal Index 0.6 0.7 0.8 0.9 Overall Rating 0.82 0.78 0.75 0.72

[0140] Through analysis, it was found that the manufacturing plant's "hot weather" and "peak power consumption time" paths scored high, suggesting that the cooling system efficiency needs to be strengthened to cope with the surge in energy consumption during high temperatures. The introduction of new entities "power consumption trend area" and "affected by geographical location" provides a scientific basis for future power consumption forecasts and strategy adjustments.

[0141] The data from the implementation example shows that after integrating third-party data, the availability and consistency of data are significantly improved through standardized processing. For example, after considering the impact of meteorology, the raw material supplier found that the peak electricity consumption period in summer is 1 hour earlier than in other seasons, which provides a basis for adjusting the start and stop time of the refrigeration system, and is expected to save about 5% of air conditioning power consumption.

[0142] Using GIS technology, the electricity consumption patterns and geographical location characteristics of each link are intuitively displayed. For example, manufacturing plants near rivers show higher humidity sensitivity, resulting in large fluctuations in the rate of change of electricity consumption. By adjusting the working strategy of moisture-proof equipment, unnecessary energy consumption caused by humidity is successfully reduced, reducing maintenance costs.

[0143] The constructed spatiotemporal knowledge graph reveals the association between abnormal equipment status and specific time periods. For example, logistics distribution equipment experiences abnormal power consumption peaks on the eve of holidays. Graph path reasoning reveals that this is related to increased stocking demand, which optimizes inventory management strategies and avoids excessive power supply during non-production periods.

[0144] According to the comprehensive scoring formula, the terminal sales link scored low, mainly due to the high load peak-to-valley ratio and the mismatch of seasonal index. By adjusting the production shift to the nighttime low period and introducing a seasonal energy management system, the comprehensive score increased by 20%, significantly reducing energy costs.

[0145] In summary, the present invention provides a comprehensive intelligent solution for industrial chain electricity management by integrating multi-source data, spatiotemporal visualization analysis, knowledge graph construction, and comprehensive scoring evaluation. Compared with traditional single-dimensional monitoring, the present invention can more deeply explore the inherent laws of electricity consumption behavior and guide energy consumption optimization in actual operations.

[0146] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for evaluating electricity consumption behavior in an industrial chain based on knowledge graph, characterized in that: include: Collect the full-link power monitoring data of the industrial chain, integrate third-party data, and store the pre-processed data in the database; Use GIS technology to integrate geographic location information and visually display spatiotemporal data on maps to perform preliminary feature extraction and visualization analysis; Based on the analysis results, define entity and relationship information and build a spatiotemporal knowledge graph; A path reasoning algorithm is used to find the relationship path between features in the spatiotemporal knowledge graph, obtain the optimal relationship path between features, and identify the core features directly related to electricity consumption behavior; The feature construction method is applied to calculate the comprehensive score of the core characteristics of electricity consumption behavior and evaluate the electricity consumption behavior of the industrial chain.

2. The method for evaluating electricity consumption behavior of an industrial chain based on a knowledge graph according to claim 1, characterized in that: The collection of full-link electricity monitoring data of the industrial chain and integration of third-party data include selecting suitable IoT sensor types according to the structural characteristics of the industrial chain to ensure coverage of electricity usage in the entire link, formulating a detailed deployment plan, physically installing the sensors according to the deployment plan, configuring network connections, completing the stable transmission of data from the sensors to the database, integrating third-party data, establishing an API interface with meteorological service providers and public holiday databases, and automatically obtaining meteorological data and holiday information at a regular interval and synchronizing them to the database.

3. The method for evaluating electricity consumption behavior of an industrial chain based on a knowledge graph as claimed in claim 2, characterized in that: Set up a data receiving port in the database, perform format check and standardization conversion on the received raw data, ensure that all data follows a unified data model, and implement data cleaning processing.

4. The method for evaluating electricity consumption behavior of an industrial chain based on a knowledge graph as claimed in claim 3 is characterized by: The use of GIS technology to integrate geographic location information and visually display spatiotemporal data on a map, and to perform preliminary feature extraction and visualization analysis includes the following steps: Use GIS technology to match and calibrate the geographic location information collected by the sensor with the physical coordinates of the monitoring point to ensure the accuracy of the geographic location data; Use GIS tools to create spatiotemporal data layers, define time series animations, and overlay meteorological data and holiday markers to map spatiotemporal data onto two-dimensional or three-dimensional maps to achieve an intuitive display of electricity consumption status; On the map interface, through heat maps and trajectory analysis methods, the electricity consumption characteristics of hot spots, peak electricity consumption periods and weather-related electricity consumption patterns are preliminarily extracted, and a visual analysis of electricity consumption distribution overview, time series trends and correlation analysis with third-party data is conducted.

5. The method for evaluating electricity consumption behavior of an industrial chain based on a knowledge graph as claimed in claim 4, characterized in that: The construction of the knowledge graph includes the following steps: Determine the core entities of the knowledge graph, including enterprises, devices, geographic locations, and timestamps; Define entity relationship information and convert it into the triple data required for the knowledge graph, including the enterprise to which the equipment belongs, the geographical location of the equipment, and the changes in power consumption status over time; Use the graph database to import triple data, build an initial static knowledge graph, and design attribute labels for each entity and relationship; Deploy a real-time data stream processing framework to receive real-time monitoring data and third-party data from IoT sensors. The data stream is decoded and formatted and converted into graph update instructions. When a change in power consumption status or an update in geographic location is detected, the update of graph nodes or edges is triggered. Each update operation includes adding, modifying or deleting nodes and edges in the graph. At the same time, the time series nodes are maintained to record the historical trajectory of status changes. New entities are introduced into the map, including power consumption trend areas and those affected by geographic location. Power consumption trend areas predict the future power consumption trend of the equipment based on the power consumption data of each device, and the prediction results are added as new map attributes. The influence of geographic location uses GIS tools to analyze the impact of geographic location characteristics on power consumption patterns.

6. The method for evaluating electricity consumption behavior of an industrial chain based on a knowledge graph according to claim 5, characterized in that: The method of using the path inference algorithm to find the relationship path between features in the spatiotemporal knowledge graph includes the following steps: Define the logical connections between entities and relations in the spatiotemporal knowledge graph; Define the use of a graphical interface to display feature relationship paths, where nodes represent features, edges represent relationships, edge width reflects the strength of the relationship, and edge color reflects the nature of the relationship; Find the target feature of the relationship path, set it as the end node, select one or more features as the starting node, start the search, and each time the node is expanded, select the next exploration node based on the actual cost from the starting node to the current node and the shortest path length from the current node to the target node; Sort all valid paths found, and prioritize those with shorter path lengths, higher rule matching, and more logically direct paths; Identify the core features directly related to electricity usage behavior, analyze the nodes and edges on the optimal path, and map them to the features related to specific electricity usage behavior.

7. The method for evaluating electricity consumption behavior of an industrial chain based on a knowledge graph according to claim 6, characterized in that: The application feature construction method, calculating the comprehensive score of the core features of electricity consumption behavior, and evaluating the electricity consumption behavior of the industrial chain includes the following steps: Define basic time series features and user attribute features. Basic time series features include daily electricity consumption D daily , Peak power consumption time T peak and load curve slope S slope , user attribute characteristics include industry category code C industry and geographic location code D location ; Construct composite features, power consumption change rate CR change , Load Peak-to-Valley Ratio PVR peak-valley and seasonal index SI seasonal ; Set scoring indicators to quantify the strength of association between characteristics and electricity consumption behavior; The comprehensive score of the core characteristics of electricity consumption behavior is expressed as: Among them, γ is the parameter of the control function steepness; Ω is the environmental influence function, Λ weather is the actual impact intensity of meteorological conditions, Λ weather-max is the greatest impact intensity of meteorological conditions in history, Λ holiday is the actual impact intensity of holidays, Λ holiday-max is the maximum impact intensity of holidays in history, β1 and β2 are adjustment coefficients, is a composite eigenvector The weighted combination function reflects the comprehensive contribution of different features to the comprehensive score. is the normalized value of the ith feature, ω i is a weight vector, indicating the importance of the i-th feature in the comprehensive score, n is the total number of features, is the daily electricity consumption D daily After normalization, the value is the peak power consumption time T peak After normalization, the value is the load curve slope S slope After normalization, the value Industry category code C industry After normalization, the value is the geographic location code D location After normalization, the value is the rate of change of power consumption CR change After normalization, the value is the load peak-to-valley ratio PVR peak-valley After normalization, the value is the seasonal index SI seasonal The normalized value; Based on the comprehensive scoring results, analyze the industry chain for high electricity efficiency, large optimization space, or abnormal electricity usage behaviors; When S = 0, it means that the electricity efficiency is extremely low and there are serious problems with electricity usage in the industrial chain; When S < 0.5, it means that the electricity efficiency is low and there are specific problem areas in the electricity consumption behavior in the industrial chain; When S>0.7, it means that although the electricity efficiency is good, there is still room for fine-tuning the electricity consumption behavior in the industrial chain; When S=1, it means that the electricity consumption efficiency is extremely high and the electricity consumption behavior in the industrial chain is in efficient operation.

8. An industrial chain electricity consumption behavior evaluation system based on a knowledge graph as claimed in any one of claims 1 to 7, characterized in that: It includes data collection module, visualization analysis module, spatiotemporal knowledge graph construction module, optimal path search module, and industrial chain electricity consumption evaluation module; The data collection module is used to collect the full-link power monitoring data of the industrial chain, integrate third-party data, and store the pre-processed data in the database; The visualization analysis module is used to integrate geographic location information using GIS technology, and to visually display spatiotemporal data on a map, and to perform preliminary feature extraction and visualization analysis; The spatiotemporal knowledge graph construction module is used to define entity and relationship information based on the analysis results and construct a spatiotemporal knowledge graph; The optimal path finding module is used to find the relationship path between features in the spatiotemporal knowledge graph using a path reasoning algorithm, obtain the optimal relationship path between features, and identify the core features directly related to the electricity consumption behavior; The module for evaluating electricity consumption in the industrial chain is used to apply a feature construction method, calculate a comprehensive score of the core features of electricity consumption behavior, and evaluate the electricity consumption behavior of the industrial chain.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for evaluating electricity consumption behavior of an industrial chain based on a knowledge graph as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for evaluating electricity consumption behavior of an industrial chain based on a knowledge graph as described in any one of claims 1 to 7 are implemented.

Citation Information

Cited By

  • Electricity purchase structure adjustment method and system

    CN119648471A

  • Industrial chain atlas modeling method and system based on deep learning

    CN120012897A

  • A Modeling Method and System for Industrial Chain Maps Based on Deep Learning

    CN120012897B

  • Energy power data asset assessment method based on artificial intelligence

    CN120216569A

  • Urban electricity utilization evaluation method based on electric power big data and related device

    CN120297573A