A method and apparatus for generating profiles of power supply entities

Abstract

This invention discloses a method and apparatus for generating profiles of power supply entities. The method includes: acquiring static supply capacity data, dynamic supply capacity data, and environmental impact data of each supply entity and performing entity identification to obtain static entities, dynamic entities, and environmental event entities; establishing a supply profile map based on the supply relationships between static entities, combined with changes in dynamic entities and the occurrence of environmental event entities; updating the supply profile map by using a risk propagation model to obtain the propagation path of real-time environmental impact data; and extracting static and dynamic indicator values ​​from the updated supply profile map to provide a profile of the supply entity. By constructing a supply profile map through a two-way influence mechanism of environmental event entities and dynamic entities, the method dynamically generates profiles of power supply entities and updates them based on environmental event entities, providing a scientific basis for selecting power supply entities with strong risk resistance capabilities.

Description

Technical Field

[0001] This invention belongs to the technical field of data processing, specifically relating to a method and apparatus for generating a profile of a power material supply entity. Background Technology

[0002] The power system is a crucial component of the national infrastructure, and its safe operation is directly related to social stability and economic development. The quality and reliability of power equipment (such as transformers, high-voltage switches, and cables) are paramount. Any quality defects or malfunctions can lead to serious safety accidents and even affect the safe operation of the entire power grid. The high safety sensitivity of power equipment requires suppliers to have rigorous quality control systems and comprehensive quality testing processes to ensure that the supplied materials meet national and industry standards.

[0003] In related technologies, by building supplier profiles, companies can gain a more comprehensive understanding of suppliers’ supply capabilities, supply quality, reputation and risk resistance, thus making more informed choices. Accurate supplier profiles help companies predict potential problems in the supply chain and take corresponding measures or preventative actions in advance.

[0004] Patent application CN119990924A discloses a method and system for constructing a dynamic multi-dimensional supplier profile, including: obtaining the initial delivery quality value of the target supplier at a target time; obtaining the similarity value between the target supplier and reference suppliers in terms of the initial delivery quality value; using the similarity value corresponding to the reference supplier as a weight, weighted summing of the delivery quality feature values ​​of different reference suppliers of the target supplier to obtain an adjustment coefficient; multiplying the initial delivery quality value of the target supplier at the target time by the adjustment coefficient to obtain the delivery evaluation value of the target supplier at the target time. Based on the delivery evaluation values ​​of the target supplier at different times, the construction result of the target supplier profile can be determined, thereby realizing the construction of supplier profiles for supplier management.

[0005] Among the aforementioned technologies, profiling suppliers solely based on delivery quality is not comprehensive enough and has limited accuracy.

[0006] Improving the accuracy of supplier profiles to ensure the stability and efficiency of the power supply chain and obtain high-quality products and services is a problem that needs to be solved. Summary of the Invention

[0007] To address the shortcomings of existing technologies, this invention provides a method and apparatus for generating profiles of power supply entities. The method includes: acquiring static supply capacity data, dynamic supply capacity data, and environmental impact data for each supply entity; performing entity identification on the static supply capacity data, dynamic supply capacity data, and environmental impact data to obtain static entities, dynamic entities, and environmental event entities; establishing a supply profile map based on the supply relationships between static entities, combined with changes in dynamic entities and the occurrence of environmental event entities; updating the supply profile map by using a risk propagation model to obtain the propagation path of real-time environmental impact data and adjusting the weights of relationships between entities in the supply profile map; and extracting static and dynamic indicator values ​​from the updated supply profile map and providing the corresponding supply entity profiles. By constructing a supply profile map and a two-way influence mechanism between risk (environmental event entities) and indicators (dynamic entities), a profile of power supply entities is dynamically generated and updated in a timely manner according to risk events. This provides a scientific basis for power grid companies to select power supply entities with strong risk resistance capabilities while also improving the accuracy of the supply entity profiles.

[0008] In a first aspect, the present invention provides a method for generating a profile of a power supply entity, which specifically includes the following steps:

[0009] Obtain static supply capacity data, dynamic supply capacity data, and environmental impact data from each supply entity;

[0010] Entity identification is performed on static supply capacity data, dynamic supply capacity data, and environmental impact data respectively to obtain static entities, dynamic entities, and environmental event entities;

[0011] Based on the supply relationships between static entities, and combined with the changes in dynamic entities and the occurrence of environmental events, a supply profile map is established.

[0012] Based on the supply profile map, a risk propagation model is used to obtain the propagation path of real-time environmental impact data, and the relationship weights between various entities in the supply profile map are adjusted to update the supply profile map.

[0013] Extract static and dynamic indicator values ​​from the updated supply profile map, and provide the supply entity profiles corresponding to the static and dynamic indicator values.

[0014] Furthermore, based on the supply relationships between static entities, combined with the changes in dynamic entities and the occurrence of environmental events, a supply profile map is established, specifically including:

[0015] Establish the first supply map based on the supply relationships between static entities;

[0016] Based on the degree of association between dynamic and static entities and the changes in dynamic entities, dynamic entities are added to the first supply map and the corresponding relationship weights of the dynamic entities are adjusted to obtain the second supply map.

[0017] Based on the occurrence of environmental event entities and their impact on static and / or dynamic entities, environmental event entities are added to the second supply map, and the corresponding relationship weights are configured to obtain the supply profile map.

[0018] Furthermore, based on the occurrence of environmental event entities and their impact on static and / or dynamic entities, environmental event entities are added to the second supply map, and corresponding relationship weights are configured to obtain a supply profile map, specifically including:

[0019] Based on the occurrence of the environmental event entity, identify the static and / or dynamic entities directly affected by the environmental event entity;

[0020] Analyze the degree of influence of environmental event entities on static and / or dynamic entities, and assign corresponding relationship weights to the association between environmental event entities and static and / or dynamic entities;

[0021] Based on a preset relationship decreasing function, and combined with the relationship weights of static entities and / or dynamic entities with environmental event entities, the relationship weights of static entities and / or dynamic entities with other entities are adjusted to obtain an initial profile map.

[0022] Traverse each static entity in the initial image graph, analyze and determine the relationship weight between each static entity and dynamic entities and / or environmental event entities;

[0023] If the relationship weight between a static entity and a dynamic entity and / or an environmental event entity is lower than a preset relationship threshold, the association between the static entity and the dynamic entity and / or the environmental event entity is deleted based on the latest update time of the dynamic entity and / or the environmental event entity, thus obtaining a supply profile map.

[0024] Furthermore, based on the supply profile graph, a risk propagation model is adopted to obtain the propagation path of real-time environmental impact data, and the relationship weights between various entities in the supply profile graph are adjusted according to the real-time environmental impact data to update the supply profile graph. Specifically, this includes:

[0025] Based on real-time environmental impact data, identify the corresponding environmental event entities in the supply profile map;

[0026] Based on the environmental event entities, multidimensional features of real-time environmental impact data are extracted to construct an impact vector. The multidimensional features include spatial features, temporal features, and intensity features.

[0027] The impact vector of real-time environmental impact data is matched with the attributes of entities in the supply profile map to identify affected entities and generate initial propagation paths.

[0028] Based on the initial propagation path, and combined with the impact scope of environmental event entities and the relationships between various entities in the supply profile, a risk propagation model is used to simulate the risk propagation process and generate the optimal propagation path.

[0029] Based on the occurrence frequency of environmental event entities, the relation weights on the optimal propagation path are updated to complete the update of the supply profile map.

[0030] Furthermore, based on the initial propagation path, and combining the influence scope of environmental event entities and the relationships between various entities in the supply profile, a risk propagation model is used to simulate the risk propagation process, generating an optimal propagation path. Based on the frequency of occurrence of environmental event entities, the relationship weights on the optimal propagation path are updated, specifically including:

[0031] Determine the initial impact area based on the spatial characteristics of the environmental event entity;

[0032] Based on the initial propagation path, starting from the initial area of ​​impact, and combined with the propagation intensity attenuation mechanism, a risk propagation model is adopted to simulate the risk propagation process according to the relationship between various entities in the supply profile map, and generate a basic propagation path.

[0033] Obtain the path influence of the basic propagation path, and combine it with the preset influence threshold to filter out reliable propagation paths;

[0034] Based on preset merging rules, reliable propagation paths are merged to obtain the optimal propagation path;

[0035] Based on a preset weight increment function, and combined with the occurrence frequency of environmental event entities, the unit increment weight is obtained.

[0036] The current incremental weight is obtained by combining the unit incremental weight and the distance coefficient between the environmental event entity and the current entity;

[0037] The relation weights of the current entity are adjusted based on the current incremental weights to complete the update of relation weights on the optimal propagation path.

[0038] Furthermore, static indicator values, dynamic indicator values, and event propagation paths are extracted from the updated supply profile map, and corresponding supply entity profiles are provided, specifically including:

[0039] Each static indicator value is treated as a separate dimension to construct a static radar chart;

[0040] Compare and analyze the values ​​of each dynamic indicator with the corresponding preset dynamic range, select the corresponding color from the preset presentation level colors, and generate a dynamic heat map.

[0041] Extract basic information about the supply entities and the event propagation path, and combine static radar charts and dynamic heat maps to create a profile of the supply entities.

[0042] Furthermore, the event propagation path of the supply entity is extracted, specifically including:

[0043] Centered on the static entity corresponding to the supply entity, at least one primary propagation entity is determined by filtering according to the relationship weight with each entity;

[0044] The second-level propagation entities are determined by taking the primary propagation entity as the center and combining the relationship weights between the primary propagation entity and each other entity;

[0045] Repeat the process of determining the propagation entity until the latest propagation entity is the environmental event entity, and obtain the event propagation path from the environmental event entity to the static entity corresponding to the supply subject.

[0046] Furthermore, static indicator values ​​include at least one of qualification coverage, technical compliance rate, and historical performance score, while dynamic indicator values ​​include at least one of supply chain resilience index, quality risk score, and public opinion risk index.

[0047] Furthermore, the dynamic indicator values ​​are compared and analyzed with their corresponding preset dynamic ranges. A corresponding color is selected from the preset presentation level colors to generate a dynamic heatmap, specifically including:

[0048] Multiple sets of dynamic indicator values ​​are obtained based on profile change indicators;

[0049] Using the portrait change index as the vertical axis and the dynamic index as the horizontal axis;

[0050] Each dynamic indicator value is judged sequentially. If the dynamic indicator value is lower than the corresponding preset dynamic range, the first image color is used to represent it.

[0051] If the dynamic indicator value is higher than the corresponding preset dynamic range, the second image color will be used to represent it.

[0052] If the dynamic indicator value is within the corresponding preset dynamic range, the color of the image is determined and displayed based on the image color mapping function;

[0053] Iterate through each dynamic indicator value to generate a dynamic heatmap.

[0054] Secondly, the present invention also provides an apparatus for generating a profile of a power supply entity, employing a method for generating a profile of a power supply entity as described in any of the above-mentioned methods, including:

[0055] The data acquisition module is used to acquire static supply capacity data, dynamic supply capacity data, and environmental impact data of each supply entity.

[0056] The entity recognition module is used to perform entity recognition on static supply capacity data, dynamic supply capacity data and environmental impact data respectively, to obtain static entities, dynamic entities and environmental event entities;

[0057] The graph construction module is used to build a supply profile graph based on the supply relationships between static entities, combined with the changes in dynamic entities and the occurrence of environmental event entities.

[0058] The graph update module is used to update the supply profile graph by adopting a risk propagation model, obtaining the propagation path of real-time environmental impact data, adjusting the weights of the relationships between various entities in the supply profile graph, and updating the supply profile graph.

[0059] The profile output module is used to extract static and dynamic indicator values ​​from the updated supply profile map and provide the corresponding supply entity profiles for the static and dynamic indicator values.

[0060] The present invention provides a method and apparatus for generating a profile of a power supply entity, which has at least the following beneficial effects:

[0061] (1) Static entities, dynamic entities and environmental event entities are obtained based on entity recognition and a supply profile map is established; based on the supply profile map, a risk propagation model is adopted to obtain the propagation path of real-time environmental impact data, the supply profile map is updated and a supply entity profile is given based on the updated supply profile map, the power material supply entity profile is dynamically generated, and it is updated in a timely manner according to the environmental event entities, which provides a scientific basis for the power grid company to select power material supply entities with strong risk resistance capabilities, and also improves the accuracy of the supply entity profile.

[0062] (2) By acquiring real-time environmental impact data and determining the corresponding environmental event entities based on this, the relationship weights of relevant entities in the supply profile map are adjusted, and the supply profile map is updated in a timely manner to ensure the accuracy of the supply entity profile and provide a data foundation for the stability and efficiency of the power material supply chain.

[0063] (3) By extracting various indicator values ​​and event propagation paths from the supply profile map, and converting the various indicator values ​​into static radar charts and dynamic heat maps, and combining them with the event propagation paths for comprehensive display, the supply entity profile is displayed more comprehensively and intuitively, which helps to analyze and understand complex profile data. Attached Figure Description

[0064] Figure 1A flowchart of a method for generating a profile of a power material supply entity provided in an embodiment of the present invention;

[0065] Figure 2 This is a schematic diagram of the structure of the supply image map provided in an embodiment of the present invention;

[0066] Figure 3 A flowchart for establishing a supply profile map is provided in this embodiment of the invention;

[0067] Figure 4 A flowchart for adding environmental event entities provided in an embodiment of the present invention;

[0068] Figure 5 A flowchart for updating the supply profile map provided in an embodiment of the present invention;

[0069] Figure 6 A flowchart for generating a supplier profile provided in an embodiment of the present invention;

[0070] Figure 7 This is a structural block diagram of the power material supply entity portrait generation device provided in an embodiment of the present invention.

[0071] Among them, 201 is the data acquisition module; 202 is the entity recognition module; 203 is the map construction module; 204 is the map update module; and 205 is the image output module. Detailed Implementation

[0072] To better understand the above technical solutions, a detailed description of the solutions will be provided below in conjunction with the accompanying drawings and specific embodiments. Obviously, the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0073] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0074] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0075] A supplier is an external organization or individual that provides products, services, raw materials, components, or other resources to a power company. Based on the different services or products provided, suppliers can be categorized as raw material suppliers, component suppliers, finished product suppliers, service suppliers, and technology suppliers, among others.

[0076] In the context of bidding and procurement of power supplies, the bidding party (usually a power company or grid enterprise) needs to select the most suitable supplier through a scientific and reasonable bidding process. This is not only to ensure the quality and stability of the supply of materials, but also to optimize procurement costs and improve procurement efficiency.

[0077] The bidding and procurement process must strictly comply with national laws, regulations, and industry standards to ensure fairness, impartiality, and transparency. Suppliers should possess valid business licenses and relevant qualification certificates, such as production licenses and quality certifications. Furthermore, suppliers should have no record of illegal or irregular activities and possess a good reputation.

[0078] Electricity supplies are characterized by high safety sensitivity, long life cycle and strong planning, which place higher demands on the supply entities.

[0079] The procurement and supply of power equipment must strictly adhere to plans to ensure the smooth construction and operation of the power grid. Power projects typically have clear timelines and schedule requirements, necessitating suppliers with strong planning execution and supply chain management capabilities. Suppliers should possess efficient supply chain management systems capable of accurate forecasting and inventory management. Furthermore, suppliers should have a good delivery record with no instances of delayed delivery.

[0080] At the same time, through in-depth analysis of suppliers, companies can identify potential risk factors. For example, they can discover whether suppliers have financial instability or delivery quality issues, allowing them to adaptively select suppliers with better supply capabilities, thereby improving their ability to withstand risks.

[0081] This invention provides a method and apparatus for generating profiles of power material suppliers. The method includes: acquiring static supply capacity data, dynamic supply capacity data, and environmental impact data of each supplier; performing entity identification on the static supply capacity data, dynamic supply capacity data, and environmental impact data to obtain static entities, dynamic entities, and environmental event entities; establishing a supply profile map based on the supply relationships between static entities, combined with changes in dynamic entities and the occurrence of environmental event entities; updating the supply profile map by using a risk propagation model based on the real-time environmental impact data and adjusting the weights of the relationships between entities in the supply profile map; extracting static and dynamic indicator values ​​from the updated supply profile map and providing supplier profiles corresponding to the static and dynamic indicator values. By constructing a two-way influence mechanism between the supply profile map, risk (environmental event entities), and indicators, a profile of power material suppliers is dynamically generated and updated in a timely manner according to risk events. This provides a scientific basis for power grid companies to select power material suppliers with strong risk resistance capabilities. The environmental event entities are used to clarify the supply chain resilience of the suppliers, explicitly demonstrating their ability to withstand supply chain disruptions and improving the accuracy of the supplier profiles.

[0082] like Figure 1 As shown in the figure, this embodiment of the invention provides a method for generating a profile of a power material supply entity, and the specific steps are as follows:

[0083] S101: Obtain static supply capacity data, dynamic supply capacity data, and environmental impact data for each supply entity.

[0084] Specifically, static supply capacity data refers to data reflecting the supply capacity of a supplier, and this data is unlikely to change significantly in a short period. Static supply capacity data includes supplier qualifications, historical supply chain performance, and material inventory capacity. Supplier qualifications include the number of backup secondary suppliers and alternative supply plans. Historical supply chain performance includes the average number of delivery delays due to material issues and the supply chain emergency response time. Material inventory capacity includes the number of days of regular material inventory and the amount of strategic material reserves.

[0085] Dynamic supply capacity data reflects supply entity data that reflects market changes or is affected by market changes, and this data is subject to significant fluctuations due to market conditions. Dynamic supply capacity data includes commodity prices, the status of secondary supply entities, material supply data, and production plan matching degree. Commodity prices include core material prices such as Shanghai copper futures and silicon steel prices. The status of secondary supply entities includes their capacity utilization rate, whether there have been production stoppages / strikes, and logistical delays. Material supply data includes material delivery cycles and supply disruption warning signals. Production plan matching degree refers to the degree of alignment between the supply entity's production plan and the power grid's material demand plan.

[0086] Environmental impact data refers to data related to the environment or events that may affect the supply capacity of suppliers. Environmental impact data includes geospatial data, macro-environmental data, and supply chain topology data. Geospatial data includes factory coordinates and logistics hub locations; macro-environmental data includes typhoon paths; and supply chain topology data includes equity relationships among multiple levels of suppliers and alternative pathways.

[0087] S102: Perform entity identification on static supply capacity data, dynamic supply capacity data and environmental impact data respectively to obtain static entities, dynamic entities and environmental event entities.

[0088] By using a pre-built entity recognition model, entity recognition is performed on static supply capacity data, dynamic supply capacity data, and environmental impact data, respectively. The aforementioned entity recognition model is a pre-trained model using relevant power material data. Depending on the actual situation and needs, it can be trained using machine learning models, such as Hidden Markov Models (HMMs) and Conditional Random Fields (CRFs), or deep learning models, such as Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) Networks, and Gated Recurrent Units (GRUs). There are no limitations on the specific methods used.

[0089] Entity identification is performed on static supply capacity data to obtain static entities, such as the final supplier, secondary suppliers providing materials to the final supplier, product names such as transformers and switches, and material names such as copper and silicon steel. It is understandable that static entities include attributes.

[0090] Entity identification is performed on dynamic supply capacity data to obtain dynamic entities, such as material prices for various materials, material delivery cycles for various suppliers, and capacity utilization rates of secondary suppliers. It is understandable that dynamic entities include attributes.

[0091] Entity identification is performed on environmental impact data to obtain environmental event entities. Examples include supply chain risk events such as rising copper prices and typhoons, geographical locations such as the locations of supplier factories and logistics hubs, and policies such as new industry regulations and tariff policies. It is understandable that environmental event entities include attributes.

[0092] S103: Based on the supply relationships between static entities, combined with the changes in dynamic entities and the occurrence of environmental event entities, establish a supply profile map.

[0093] A structural diagram of the supply image atlas, such as... Figure 2 As shown, circles represent static entities, which form the basis of the supply profile map; rectangles represent dynamic entities, which are linked to the static entities; and decorative rectangles represent environmental event entities, which are added according to the actual occurrence and are linked to the static and / or dynamic entities.

[0094] Specifically, based on the supply relationships between static entities, combined with the changes in dynamic entities and the occurrence of environmental events, a supply profile map is established, referring to... Figure 3 Specifically, it includes:

[0095] Establish the first supply map based on the supply relationships between static entities;

[0096] Based on the degree of association between dynamic and static entities and the changes in dynamic entities, dynamic entities are added to the first supply map and the corresponding relationship weights of the dynamic entities are adjusted to obtain the second supply map.

[0097] Based on the occurrence of environmental event entities and their impact on static and / or dynamic entities, environmental event entities are added to the second supply map, and the corresponding relationship weights are configured to obtain the supply profile map.

[0098] Understandably, the relationships between static entities are relatively stable, forming the foundation for building a knowledge graph and serving as a prerequisite for relationships between dynamic entities and environmental event entities. Therefore, the first step is to establish a first supply graph based on the supply relationships between static entities. After obtaining the first supply graph, dynamic entities are added to it. For example, a dynamic entity for "price" is added to the various materials of the static entities, establishing relationships between materials and prices. Similarly, a dynamic entity for "supply cycle" is added to the supply entities of the static entities, establishing relationships between each supply entity and its supply cycle. After establishing the relationships between dynamic and static entities, the relationship weights corresponding to the dynamic entities need to be defined and adjusted to obtain the second supply graph.

[0099] The initial relationship weights between dynamic and static entities are defined based on the requirements of the bidding process. For example, if the project has a long operating cycle and a long delivery cycle, the relationship weight corresponding to the delivery cycle can be appropriately lowered; conversely, if the project has a short operating cycle and a tight delivery cycle, the relationship weight corresponding to the delivery cycle can be increased. As another example, if the project has sufficient start-up capital, the relationship weight corresponding to material prices can be appropriately lowered; conversely, if the project has limited start-up capital, the relationship weight corresponding to material prices can be appropriately increased.

[0100] After obtaining the second supply map, all bidding-related data can be reflected in it. However, some events can directly or indirectly affect static or dynamic entities in the second supply map. To create a more accurate profile of the supply entities, environmental event entities are introduced into the second supply map. When an environmental event occurs, based on its impact on static and / or dynamic entities, the environmental event entity is added to the second supply map, and its corresponding relationship weights are configured to obtain the supply profile map. For example, during the bidding process, the promulgation of new policies or the occurrence of news may cause the prices of certain materials to rise or fall, thus affecting the bidding process. Another example is the occurrence of natural disasters during the bidding process, which may cause some suppliers' factories to malfunction or warehouses to be unable to ship goods normally, affecting the supply cycle of certain materials. The relationship weights corresponding to environmental event entities are set based on historical experience and actual circumstances, and are not subject to any restrictions.

[0101] In a specific example, the relationships between static entities include secondary supplier A supplying material B, material B being used for product C, and final supplier D producing product C. For instance, Wuhan Silicon Steel (a secondary supplier) supplies grain-oriented silicon steel (material), which is used in transformers (products), and Yangtze Electric (the final supplier) produces transformers (products). The relationships between environmental event entities and static / dynamic entities include the factory location of the secondary supplier (a static entity) (environmental event entity), the impact of relevant policies (environmental event entity) on the processing plant (static entity), and the impact of risk events (environmental event entity) on material prices (dynamic entity), etc. For example, Wuhan Silicon Steel (a secondary supplier) is located in Wuhan (factory location), the Yangtze River Delta power rationing policy (relevant policy) affects Jiangsu copper processing plants (processing plants), and the risk event causes copper prices to rise (material prices).

[0102] Furthermore, based on the occurrence of environmental event entities and their impact on static and / or dynamic entities, environmental event entities are added to the second supply map, and corresponding relationship weights are configured to obtain a supply profile map. Figure 4 Specifically, it includes:

[0103] Based on the occurrence of the environmental event entity, identify the static and / or dynamic entities directly affected by the environmental event entity;

[0104] Analyze the degree of influence of environmental event entities on static and / or dynamic entities, and assign corresponding relationship weights to the association between environmental event entities and static and / or dynamic entities;

[0105] Based on a preset relationship decreasing function, and combined with the relationship weights of static entities and / or dynamic entities with environmental event entities, the relationship weights of static entities and / or dynamic entities with other entities are adjusted to obtain an initial profile map.

[0106] Traverse each static entity in the initial image graph, analyze and determine the relationship weight between each static entity and dynamic entities and / or environmental event entities;

[0107] If the relationship weight between a static entity and a dynamic entity and / or an environmental event entity is lower than a preset relationship threshold, the association between the static entity and the dynamic entity and / or the environmental event entity is deleted based on the latest update time of the dynamic entity and / or the environmental event entity, thus obtaining a supply profile map.

[0108] It is understandable that the relationships between the various entities are a network structure. When an environmental event occurs, it may simultaneously affect multiple static and / or dynamic entities. Changes in static or dynamic entities will in turn affect other entities associated with them, thereby affecting the initial profile map.

[0109] In one specific implementation, when an environmental event entity occurs for the first time or is added, the relational weights of the corresponding relationships of the environmental event entity are initially configured. This initial configuration is set by relevant personnel based on experience and actual circumstances. It is understood that other entities in the initial profile graph will also be indirectly affected by the environmental event entity, and the relational weights of these indirectly affected entities are adjusted according to the corresponding relational decrement function.

[0110] The relational decreasing function is specifically expressed as:

[0111]

[0112] Where x is the distance between the environmental event entity and the entity whose relation weights need to be adjusted. current This is for the entity whose relationship weight needs to be adjusted.

[0113] The distance between the aforementioned environmental event entity and other entities can be the number of entities with the shortest interval, or the corresponding distance can be configured between each entity according to the actual situation; there is no limitation on this. For example, a→b→c→d→e represents the shortest interval from environmental event entity a to static entity e. Since a and e differ by four entities, x is 4. As another example, based on the actual situation, we define the distance a→b as 1, the distance b→c as 2, the distance c→d as 1, and the distance d→e as 3. In this case, the distance between a and e is 1+2+1+3=7, meaning x is 7.

[0114] It is understandable that changes in dynamic entities and environmental event entities in the initial profile will have more or less an impact on static entities. However, when profiling a supplier, only the most core content is considered, and not all entity information that has an impact is covered. Therefore, in order to improve the efficiency of supplier profile generation and facilitate information retrieval during the supplier profile generation process, dynamic entities and / or environmental event entities with weaker impact in the initial profile should be removed in a timely manner.

[0115] Because dynamic entities and environmental event entities change over time, their corresponding relationship weights are also updated. To avoid accidentally deleting relatively important relationships, the latest update time of dynamic entities and environmental event entities is used to determine if it is lower than a time threshold. If it is, it indicates that the relationship has not been updated for a long time and has a low weight, and the corresponding relationship is deleted. For example, if the current time is 17:00 and the entity protection duration is 12 hours, then the time threshold is 5:00. If the latest update time is less than 5:00, the corresponding relationship is deleted. The entity protection duration indicates the protection of the entity and / or its relationships from deletion within the corresponding time period. Different time thresholds can be set for different entities; there is no limitation on this.

[0116] S104: Based on the supply profile map, a risk propagation model is used to obtain the propagation path of real-time environmental impact data, and the relationship weights between various entities in the supply profile map are adjusted to update the supply profile map.

[0117] Specifically, refer to Figure 5 Based on real-time environmental impact data, identify the corresponding environmental event entities in the supply profile map;

[0118] Based on the environmental event entities, multidimensional features of real-time environmental impact data are extracted to construct an impact vector. The multidimensional features include spatial features, temporal features, and intensity features.

[0119] The impact vector of real-time environmental impact data is matched with the attributes of entities in the supply profile map to identify affected entities and generate initial propagation paths.

[0120] Based on the initial propagation path, and combined with the impact scope of environmental event entities and the relationships between various entities in the supply profile, a risk propagation model is used to simulate the risk propagation process and generate the optimal propagation path.

[0121] Based on the occurrence frequency of environmental event entities, the relation weights on the optimal propagation path are updated to complete the update of the supply profile map.

[0122] Understandably, real-time environmental impact data (such as typhoons, policy changes, and market fluctuations) is transformed into quantifiable and matchable impact vectors to capture the spatial, temporal, and intensity characteristics of corresponding environmental event entities. Spatial characteristics include the geographical scope and terrain adaptability of the environmental event entity; temporal characteristics include the time-series attributes of the environmental event entity (such as typhoon landfall time, duration, and propagation delay); intensity characteristics include the impact of the environmental event entity (such as typhoon wind speed and precipitation intensity) and derivative effects (such as whether the typhoon causes floods). By combining the environmental event entity, adjusting the weights of each feature, and merging them into an impact vector, the impact vector comprehensively considers all aspects of the environmental event entity's influence. By transforming the impact of environmental event entities from "vague qualitative descriptions" to "clear quantitative inputs," a foundation is laid for the accurate identification, rapid dissemination, and effective response to supply chain risks.

[0123] The system extracts and quantifies key attributes of entities from the supply chain profiling map. These key attributes include geographical attributes (such as factory latitude and longitude, and location), risk resistance attributes (such as factory disaster resistance, wind resistance level, waterproofing level, and inventory level), and supply chain attributes (supply hierarchy and topological relationships). The impact vector of environmental events is matched with entity attribute vectors across multiple dimensions to calculate a similarity score. Entities with a similarity score ≥ a threshold (e.g., 0.6) are selected, and environmental event entities are associated with these entities to generate initial propagation paths. By vectorizing key attributes such as geographic location, risk resistance, and supply chain of entities and matching them with the spatial, temporal, and intensity impact vectors of environmental event entities across multiple dimensions, the system achieves precise association between environmental event entities and affected entities, efficiently identifying truly vulnerable entities and improving the targeting and accuracy of supply chain risk warnings.

[0124] Furthermore, based on the initial propagation path, and combining the influence scope of the environmental event entities and the relationships between various entities in the supply profile, a risk propagation model is used to simulate the risk propagation process and generate the optimal propagation path, specifically including:

[0125] Determine the initial impact area based on the spatial characteristics of the environmental event entity;

[0126] Based on the initial propagation path, starting from the initial area of ​​impact, and combined with the propagation intensity attenuation mechanism, a risk propagation model is adopted to simulate the risk propagation process according to the relationship between various entities in the supply profile map, and generate a basic propagation path.

[0127] Obtain the path influence of the basic propagation path, and combine it with the preset influence threshold to filter out reliable propagation paths;

[0128] Based on preset merging rules, reliable propagation paths are merged to obtain the optimal propagation path.

[0129] Based on the spatial characteristics of environmental event entities, the initial set of affected entities is determined. A geographic information system (GIS) can be used to map the impact range of these entities, identifying the entities within that range. All entities within the impact range constitute the initial impact area. Based on the initial propagation path, starting from the initial impact area, the risk propagation process is simulated according to the topological relationships between entities in the supply chain profile (such as supply chains and logistics networks), considering the attenuation of propagation intensity, to generate a basic propagation path.

[0130] The risk propagation model can employ cellular automata, where each cell corresponds to an entity in the supply profile graph. Based on the relationships between entities in the supply profile graph, the neighbors of each cell are determined. Risk events in the risk propagation model originate from risk event entities in the supply profile graph, and the propagation direction is from upstream entities to downstream entities. Other risk propagation models can also be used; no specific limitations are specified here.

[0131] The attenuation of propagation intensity can be categorized into geographical attenuation, temporal attenuation, and hierarchical attenuation: geographical attenuation indicates that the impact intensity decreases with distance from the epicenter of the environmental event; temporal attenuation indicates that the impact intensity decreases with each level of the supply chain; and hierarchical attenuation indicates that the impact intensity decreases with each level of the supply chain. Specific rules for geographical, temporal, and hierarchical attenuation can be set based on actual circumstances and historical experience. By accurately locating directly affected entities and scientifically extrapolating the propagation path of risks along the supply chain, a more accurate basis for generating supplier profiles can be provided.

[0132] In this example, the propagation intensity is specifically represented as:

[0133]

[0134] In the formula, I end I0 represents the propagation strength at the end of the path; I0 represents the initial propagation strength of the environmental event entity, which is related to the strength characteristics of the environmental event entity; D is the topological network distance, which is the normalized cumulative distance along the supply chain path; L is the effective transmission level, referring to the number of hops at key nodes in the path, which can be counted as level 1 for core supply entities; t cThe environmental event timeliness is related to the time characteristics of the environmental event entity; τ is the entity's risk resistance coefficient, which can be determined by combining material toughness, inventory turnover rate, etc.; α, β, and γ are decay constants, which can be determined by regression fitting through methods such as training with power grid equipment supply data.

[0135] Furthermore, the topological network distance D is specifically expressed as:

[0136]

[0137] In the formula, i=0 represents the starting entity, n-1 represents the ending entity, and d （i，i+1） R represents the distance between entity i and entity i+1, and R represents the radius of influence of the environmental event.

[0138] In this example, geographical attenuation is used. It accurately reflects the mitigating effect of actual logistics routes on risk transmission, through hierarchical attenuation. Strengthen the transmission weight of key nodes (such as sole suppliers) through time decay. By dynamically capturing the interaction between time sensitivity and physical resilience (such as inventory turnover rate hedging against typhoon timeliness), the intensity of environmental events propagation in the supply chain is quantified, improving the accuracy of identifying key nodes in risk transmission, generating more realistic profiles of supply entities, and providing power grid companies with more accurate and physically reliable decision-making basis for selecting supply entities.

[0139] For the simulated basic propagation paths, their path impact is obtained. Based on a preset impact threshold, paths with high impact (high supply chain value) are selected as reliable propagation paths. Reliable propagation paths with duplicate endpoints or key nodes are then merged to output the optimal propagation path. The path impact can be obtained by combining the relationship weights between entities in the supply chain profiling graph. Specifically, it can be calculated as the product of the weights of all edges (relationships between entities in the supply chain profiling graph) from the path's starting point to its endpoint. Merging paths with duplicate endpoints or key nodes means: for two paths with the same endpoint, they are merged into "starting point → endpoint node," and the path impact is taken as the maximum of the two paths; for two paths with the same key node, they are merged into "starting point → key node → endpoint node," and the path impact is taken as the maximum or average of the two paths. Through path selection and merging, invalid paths are eliminated, and high-risk endpoint nodes are highlighted, ensuring that the propagation paths meet the supply chain risk warning requirements of "high impact and high value," reducing the number of paths and emphasizing core risks.

[0140] Furthermore, based on the occurrence frequency of environmental event entities, the relation weights on the propagation path are updated, specifically including:

[0141] Based on a preset weight increment function, and combined with the occurrence frequency of environmental event entities, the unit increment weight is obtained.

[0142] The current incremental weight is obtained by combining the unit incremental weight and the distance coefficient between the environmental event entity and the current entity;

[0143] The relationship weights of the current entity are adjusted based on the current incremental weights, thus updating the relationship weights along the propagation path.

[0144] Understandably, when the same environmental event entity occurs again or multiple times, its impact on various entities in the supply chain profile will change. Therefore, it's necessary to adjust the relationship weights of the entities directly or indirectly affected by the environmental event entity based on the frequency of its occurrence. The weight increment function is specifically expressed as follows:

[0145]

[0146] Among them, W u The weight is a unit increment, where y is the number of times an environmental event entity occurs, and W is the weight. now Let x be the relation weight between an entity and the entity at a distance x after the environmental event entity has occurred y times. now The current relation weight of the corresponding entity is given by x, which is the distance between the environmental event entity and the entity whose relation weight needs to be adjusted, and 1 / (10x) is the distance coefficient.

[0147] In one specific implementation, real-time environmental impact data is first acquired. It is then determined whether a corresponding environmental event entity exists in the supply profile graph. If so, subsequent operations are performed on the corresponding environmental event entity in the supply profile graph. If no corresponding environmental event entity exists, it needs to be added to the supply profile graph. After determining the environmental event entity corresponding to the real-time environmental impact data, the propagation path of the real-time environmental impact data is clarified based on the association between the environmental event entity and other entities in the supply profile graph. The relationship weights on the propagation path are then updated based on the frequency of occurrence of the environmental event entity.

[0148] Updating relation weights first requires calculating the unit increment weight. The unit increment weight is related to the frequency of occurrence of the environmental event entity; the more frequent the occurrence, the larger the corresponding unit increment weight, indicating that the environmental event entity is more likely to influence other entities. Conversely, the fewer the occurrences, the smaller the corresponding unit increment weight, indicating that the environmental event entity has a smaller impact on other entities. Combining the unit increment weight with the distance coefficient between the environmental event entity and the current entity, the current increment weight is obtained. It can be understood that the closer the environmental event entity is to other entities, the greater its influence; the farther away, the smaller its influence. Therefore, adjusting and obtaining the current increment weight using the distance coefficient completes the update of relation weights along the propagation path.

[0149] S105: Extract static and dynamic indicator values ​​from the updated supply profile map, and provide the supply entity profiles corresponding to the static and dynamic indicator values.

[0150] Reference Figure 6 Specifically, it includes:

[0151] Each static indicator value is treated as a separate dimension to construct a static radar chart. The static indicator values ​​include at least one of the following: qualification coverage, technical compliance rate, and historical performance score.

[0152] Compare and analyze the values ​​of each dynamic indicator with the corresponding preset dynamic range, select the corresponding color from the preset presentation level colors, and generate a dynamic heat map. The dynamic indicator values ​​include at least one of the following: supply chain resilience index, quality risk score, and public opinion risk index.

[0153] Extract basic information about the supply entities and the event propagation path, and combine static radar charts and dynamic heat maps to create a profile of the supply entities.

[0154] The qualification coverage Q is specifically expressed as:

[0155]

[0156] Among them, C Q1 For the number of final suppliers that have obtained mandatory certification, C Q2 The number of mandatory certifications required.

[0157] The technical compliance rate T is specifically expressed as:

[0158]

[0159] Among them, C T1 To ensure the number of product parameters conforming to national standards, C T2 This represents the total number of key parameters.

[0160] Historical performance rating of H, specifically means:

[0161]

[0162] Among them, H i The historical performance score of the final supplier in year i is given, where n is the number of years since the final supplier was established.

[0163] In this example, the qualification coverage is obtained from the relationship between "final supplier → qualification" in the supply profile map, the technical compliance rate is obtained from the relationship between "product → standard" in the supply profile map, and the historical performance score is obtained from the relationship between "final supplier → performance record" in the supply profile map.

[0164] The supply chain resilience index S reflects the ability of supply entities to withstand supply chain disruptions. The higher the supply chain resilience index, the greater the ability to withstand risks. Specifically, it is expressed as follows:

[0165]

[0166] Where, r ss For the risk value of secondary supply entities, r M r represents the material risk value. s For the risk value of the final supplier, r p Here, denoted as 'product risk value', 'a' as the weighting coefficient corresponding to the risk value of the secondary supplier, 'b' as the weighting coefficient corresponding to the material risk, 'c' as the weighting coefficient corresponding to the risk value of the final supplier, and 'd' as the weighting coefficient corresponding to the product risk value.

[0167] In this example, the risk value of the secondary supplier is the average of the weights of the relationships between the secondary supplier and each environmental event entity; the risk value of the material is the average of the weights of the relationships between the material and each environmental event entity; the risk value of the final supplier is the average of the weights of the relationships between the final supplier and each environmental event entity; and the risk value of the product is the average of the weights of the relationships between the product and each environmental event entity. In other implementations, the risk value of the secondary supplier can also be the sum of the changes in the weights of the relationships between the secondary supplier and each environmental event entity; the risk value of the material can also be the sum of the changes in the weights of the material relationships between each environmental event entity; the risk value of the final supplier can also be the sum of the changes in the weights of the final supplier relationships between each environmental event entity; and the risk value of the product can be the sum of the changes in the weights of the product relationships between each environmental event entity. For example, if the initial relationship weight between the secondary supplier and a certain environmental event entity is a1, and the current relationship weight is a2, then the change difference is a2 - a1. Summing the changes in the weights of the secondary supplier and each environmental event entity yields the risk value of the secondary supplier. Similarly, the risk values ​​of the material, the final supplier, and the product can be obtained, which will not be elaborated further here.

[0168] Quality Risk Score Q r Specifically, it is expressed as:

[0169]

[0170] Where, r p Let be the product risk value, D be the real-time sampling defect rate, C be the real-time customer complaint rate, e be the weighting coefficient corresponding to the product risk value, f be the weighting coefficient corresponding to the real-time sampling defect rate, and g be the weighting coefficient corresponding to the real-time customer complaint rate.

[0171] Public opinion risk index O r Specifically, it is expressed as:

[0172]

[0173] Where, r s Let L be the risk value of the final supplier, P be the number of real-time judicial disputes, h be the weighting coefficient corresponding to the risk value of the final supplier, j be the weighting coefficient corresponding to the number of real-time judicial disputes, and m be the weighting coefficient corresponding to the number of real-time administrative penalties.

[0174] Furthermore, the dynamic indicator values ​​are compared and analyzed with their corresponding preset dynamic ranges. A corresponding color is selected from the preset presentation level colors to generate a dynamic heatmap, specifically including:

[0175] Multiple sets of dynamic indicator values ​​are obtained based on profile change indicators;

[0176] Using the portrait change index as the vertical axis and the dynamic index as the horizontal axis;

[0177] Each dynamic indicator value is judged sequentially. If the dynamic indicator value is lower than the corresponding preset dynamic range, the first image color is used to represent it.

[0178] If the dynamic indicator value is higher than the corresponding preset dynamic range, the second image color will be used to represent it.

[0179] If the dynamic indicator value is within the corresponding preset dynamic range, the color of the image is determined and displayed based on the image color mapping function;

[0180] Iterate through each dynamic indicator value to generate a dynamic heatmap.

[0181] In one specific implementation, the profile change indicator can be either time or the supply entity. If the profile change indicator is time, it can display the changes in the dynamic indicator values ​​of the current supply entity at different times; if the profile change indicator is the supply entity, it can display the changes in the dynamic indicators of different supply entities at the current time. Taking the supply entity as the vertical axis and the public opinion risk index as the horizontal axis as an example, the dynamic indicator values ​​of different supply entities at the current time are obtained, that is, the dynamic indicator value of supply entity A1 is the public opinion risk index a1, the dynamic indicator value of supply entity A2 is the public opinion risk index a2, ..., and the dynamic indicator value of supply entity An is the public opinion risk index an.

[0182] The algorithm sequentially checks the preset dynamic range [b1, b2] corresponding to a1 and the public opinion risk index. If a1 is less than b1, it indicates that the dynamic indicator value is below the corresponding preset dynamic range, and the first image color is used to represent it. This image color is then displayed in the area where the vertical axis represents the supplier A1 and the horizontal axis represents the public opinion risk index a1. If a1 is within [b1, b2], it indicates that the dynamic indicator value is within the corresponding preset dynamic range. The image color mapping function is used to substitute the public opinion risk index a1 into the image mapping function to obtain the corresponding image color, and then the image color is displayed in the area where the vertical axis represents the supplier A1 and the horizontal axis represents the public opinion risk index a1. If a1 is greater than b2, it indicates that the dynamic indicator value is above the corresponding preset dynamic range, and the second image color is used to represent it. This image color is then displayed in the area where the vertical axis represents the supplier A1 and the horizontal axis represents the public opinion risk index a1. The same checks are performed for other dynamic indicator values ​​until the entire process is completed, resulting in a dynamic heatmap. In other examples, the horizontal axis can be any one or more of the supply chain resilience index, quality risk score, and public opinion risk index, without any restrictions.

[0183] By defining the first and second portrait colors, which are clearly distinct from the color range corresponding to the portrait color mapping function, we can clarify the distribution of dynamic indicator values ​​that are not within the preset dynamic range, which is helpful for further data analysis.

[0184] Furthermore, the event propagation path of the supply entity is extracted, specifically including:

[0185] Centered on the static entity corresponding to the supply entity, at least one primary propagation entity is determined by filtering according to the relationship weight with each entity;

[0186] The second-level propagation entities are determined by taking the primary propagation entity as the center and combining the relationship weights between the primary propagation entity and each other entity;

[0187] Repeat the process of determining the propagation entity until the latest propagation entity is the environmental event entity, and obtain the event propagation path from the environmental event entity to the static entity corresponding to the supply subject.

[0188] In one specific implementation, the static entity corresponding to the supplier is used as the center. Entities are filtered based on their relationship weights with each other. If the relationship weight exceeds a threshold, it indicates a closer relationship between the corresponding entity and the supplier, and it has a greater influence on the supplier; this entity is then identified as a first-level propagation entity. Next, using the first-level propagation entity as the center, the relationship weights between the first-level propagation entity and each other are checked to see if the relationship weight exceeds a threshold. If it does, it is identified as a second-level propagation entity. This process of identifying propagation entities is repeated, using the second-level propagation entity as the center, until the latest propagation entity is the environmental event entity. This yields the event propagation path from the environmental event entity to the static entity corresponding to the supplier. For example, the event propagation path could be: silicon steel price increase → Wuhan silicon steel (second-level supplier) → oriented silicon steel (material) → Yangtze Electric (final supplier) → transformer (product) → product delivery.

[0189] In a specific example, a static radar chart is drawn with qualification coverage, technical compliance rate, and historical performance score as axes. For example, technical compliance rate is 100% and qualification coverage is 89%. A dynamic heat map is drawn with supply chain resilience index, quality risk score, and public opinion risk index as dimensions, using colors to represent levels (e.g., S=0.86→light green).

[0190] Finally, the static radar chart, dynamic heat map, and event propagation path are integrated and displayed to complete the profile of the supply entity.

[0191] Reference Figure 7 This invention provides a device for generating a profile of a power supply entity, comprising:

[0192] The data acquisition module 201 is used to acquire static supply capacity data, dynamic supply capacity data, and environmental impact data of each supply entity;

[0193] The entity recognition module 202 is used to perform entity recognition on static supply capacity data, dynamic supply capacity data and environmental impact data respectively, to obtain static entities, dynamic entities and environmental event entities;

[0194] The graph construction module 203 is used to build a supply profile graph based on the supply relationships between static entities, combined with the changes in dynamic entities and the occurrence of environmental event entities.

[0195] The graph update module 204 is used to update the supply profile graph by adopting a risk propagation model, obtaining the propagation path of real-time environmental impact data, adjusting the relationship weights between various entities in the supply profile graph, and updating the supply profile graph.

[0196] The profile output module 205 is used to extract static and dynamic indicator values ​​from the updated supply profile map and provide the supply entity profile corresponding to the static and dynamic indicator values.

[0197] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the described module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0198] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention. Clearly, those skilled in the art can make various alterations and modifications to the invention without departing from its spirit and scope. Thus, if these modifications and variations of the invention fall within the scope of the claims and their equivalents, the invention is also intended to include these modifications and variations.

Claims

1. A method for generating a profile of a power supply entity, characterized in that, include: Obtain static supply capacity data, dynamic supply capacity data, and environmental impact data from each supply entity; Entity identification is performed on static supply capacity data, dynamic supply capacity data, and environmental impact data respectively to obtain static entities, dynamic entities, and environmental event entities; Based on the supply relationships between static entities, and combined with the changes in dynamic entities and the occurrence of environmental events, a supply profile map is established. Based on real-time environmental impact data, identify the corresponding environmental event entities in the supply profile map; Based on the environmental event entities, multidimensional features of real-time environmental impact data are extracted to construct an impact vector. The multidimensional features include spatial features, temporal features, and intensity features. The impact vector of real-time environmental impact data is matched with the attributes of entities in the supply profile map to identify affected entities and generate initial propagation paths. Determine the initial impact area based on the spatial characteristics of the environmental event entity; Based on the initial propagation path and starting from the initial affected area, a risk propagation model is adopted, combined with the propagation intensity attenuation mechanism, to simulate the risk propagation process according to the relationships between various entities in the supply profile map, generating a basic propagation path. The propagation intensity attenuation includes geographical attenuation, temporal attenuation, and hierarchical attenuation. The propagation intensity is specifically represented as follows: ； In the formula, I end I0 represents the initial propagation strength of the environmental event entity, D is the topological network distance, L is the effective propagation level, and t represents the propagation intensity at the end of the path. c For environmental incident time limits, The risk resistance coefficient of the entity. For constant decay, i=0 represents the starting entity, n-1 represents the ending entity, and d （i，i+1） R represents the distance between entity i and entity i+1, and R represents the radius of influence of the environmental event. Obtain the path influence of the basic propagation path, and combine it with the preset influence threshold to filter out reliable propagation paths; Based on preset merging rules, reliable propagation paths are merged to obtain the optimal propagation path; Based on the occurrence frequency of environmental event entities, update the relation weights on the optimal propagation path to complete the update of the supply profile map; Extract static and dynamic indicator values ​​from the updated supply profile map, and provide the supply entity profiles corresponding to the static and dynamic indicator values.

2. The method for generating a profile of a power supply entity as described in claim 1, characterized in that, Based on the supply relationships between static entities, and combined with the changes in dynamic entities and the occurrence of environmental events, a supply profile map is established, specifically including: Establish the first supply map based on the supply relationships between static entities; Based on the degree of association between dynamic and static entities and the changes in dynamic entities, dynamic entities are added to the first supply map and the corresponding relationship weights of the dynamic entities are adjusted to obtain the second supply map. Based on the occurrence of environmental event entities and their impact on static and / or dynamic entities, environmental event entities are added to the second supply map, and the corresponding relationship weights are configured to obtain the supply profile map.

3. The method for generating a profile of a power supply entity as described in claim 2, characterized in that, Based on the occurrence of environmental event entities and their impact on static and / or dynamic entities, environmental event entities are added to the second supply map, and corresponding relationship weights are configured to obtain the supply profile map, which specifically includes: Based on the occurrence of the environmental event entity, identify the static and / or dynamic entities directly affected by the environmental event entity; Analyze the degree of influence of environmental event entities on static and / or dynamic entities, and assign corresponding relationship weights to the association between environmental event entities and static and / or dynamic entities; Based on a preset relationship decreasing function, and combined with the relationship weights of static entities and / or dynamic entities with environmental event entities, the relationship weights of static entities and / or dynamic entities with other entities are adjusted to obtain an initial profile map. Traverse each static entity in the initial image graph, analyze and determine the relationship weight between each static entity and dynamic entities and / or environmental event entities; If the relationship weight between a static entity and a dynamic entity and / or an environmental event entity is lower than a preset relationship threshold, the association between the static entity and the dynamic entity and / or the environmental event entity is deleted based on the latest update time of the dynamic entity and / or the environmental event entity, thus obtaining a supply profile map.

4. The method for generating a profile of a power supply entity as described in claim 1, characterized in that, Based on the occurrence frequency of environmental event entities, update the relation weights on the optimal propagation path, specifically including: Based on a preset weight increment function, and combined with the occurrence frequency of environmental event entities, the unit increment weight is obtained. The current incremental weight is obtained by combining the unit incremental weight and the distance coefficient between the environmental event entity and the current entity; The relation weights of the current entity are adjusted based on the current incremental weights to complete the update of relation weights on the optimal propagation path.

5. The method for generating a profile of a power material supply entity as described in claim 1, characterized in that, Extract static and dynamic indicator values ​​and event propagation paths from the updated supply profile map, and provide corresponding supply entity profiles, including: Each static indicator value is treated as a separate dimension to construct a static radar chart; Compare and analyze the values ​​of each dynamic indicator with the corresponding preset dynamic range, select the corresponding color from the preset presentation level colors, and generate a dynamic heat map. Extract basic information about the supply entities and the event propagation path, and combine static radar charts and dynamic heat maps to create a profile of the supply entities.

6. The method for generating a profile of a power material supply entity as described in claim 5, characterized in that, Extracting the event propagation path of the supply entity, specifically including: Centered on the static entity corresponding to the supply entity, at least one primary propagation entity is determined by filtering according to the relationship weight with each entity; The second-level propagation entities are determined by taking the primary propagation entity as the center and combining the relationship weights between the primary propagation entity and each other entity; Repeat the process of determining the propagation entity until the latest propagation entity is the environmental event entity, and obtain the event propagation path from the environmental event entity to the static entity corresponding to the supply subject.

7. The method for generating a profile of a power supply entity as described in claim 5, characterized in that, Static indicators include at least one of qualification coverage, technical compliance rate, and historical performance score, while dynamic indicators include at least one of supply chain resilience index, quality risk score, and public opinion risk index.

8. The method for generating a profile of a power supply entity as described in claim 5, characterized in that, The dynamic indicator values ​​are compared and analyzed with their corresponding preset dynamic ranges. A corresponding color is selected from the preset presentation level colors to generate a dynamic heatmap, specifically including: Multiple sets of dynamic indicator values ​​are obtained based on profile change indicators; Using the portrait change index as the vertical axis and the dynamic index as the horizontal axis; Each dynamic indicator value is judged sequentially. If the dynamic indicator value is lower than the corresponding preset dynamic range, the first image color is used to represent it. If the dynamic indicator value is higher than the corresponding preset dynamic range, the second image color will be used to represent it. If the dynamic indicator value is within the corresponding preset dynamic range, the color of the image is determined and displayed by combining the image color mapping function; each dynamic indicator value is traversed to generate a dynamic heatmap.

9. A device for generating a profile of a power supply entity, characterized in that, The method for generating a profile of a power supply entity as described in any one of claims 1-8 includes: The data acquisition module is used to acquire static supply capacity data, dynamic supply capacity data, and environmental impact data of each supply entity. The entity recognition module is used to perform entity recognition on static supply capacity data, dynamic supply capacity data and environmental impact data respectively, to obtain static entities, dynamic entities and environmental event entities; The graph construction module is used to build a supply profile graph based on the supply relationships between static entities, combined with the changes in dynamic entities and the occurrence of environmental event entities. The graph update module is used to update the supply profile graph by adopting a risk propagation model, obtaining the propagation path of real-time environmental impact data, adjusting the weights of the relationships between various entities in the supply profile graph, and updating the supply profile graph. The profile output module is used to extract static and dynamic indicator values ​​from the updated supply profile map and provide the corresponding supply entity profiles for the static and dynamic indicator values.

Images