Power grid transformation project-oriented project group comprehensive evaluation method and device and medium

Abstract

The invention provides a project group comprehensive evaluation method and device for a power grid transformation project, and a medium. The method comprises the steps of obtaining related text data, geographic information system data, project historical data and power grid topological structure data; performing feature extraction and analysis on the related text data to construct a semantic feature association network; performing connection analysis on the geographic information system data and the power grid topological structure data to construct a geographic topological feature association network; performing time sequence feature analysis on the project historical data to construct a time sequence feature association network; constructing a multi-dimensional coupling network based on the semantic feature association network, the geographic topological feature association network and the time sequence feature association network; identifying a core project group from the multi-dimensional coupling network; establishing a project group comprehensive evaluation model based on the core project group; performing comprehensive evaluation on the to-be-evaluated project group through the project group comprehensive evaluation model to obtain a target project group; and evaluating the comprehensive benefit of the target project group in the power grid transformation. Therefore, the project group evaluation comprehensiveness is improved.

Description

Technical Field

[0001] The embodiments of this disclosure relate to the field of project evaluation technology, and more specifically, to a method, apparatus, and medium for comprehensive evaluation of project groups for power grid transformation projects. Background Technology

[0002] With the increasing scale and complexity of power grid construction, single projects can no longer meet the needs of modern power grid development. Driven by both "dual carbon" goals and the construction of new power systems, the tasks of power grid companies are gradually shifting from traditional "single-point investment" to the more complex "project group coordination." The collaborative management and scientific evaluation of project groups directly determine the efficiency of power grid construction, the accuracy of resource allocation, and the long-term operational stability. To improve investment efficiency and operational quality, comprehensive evaluation must be conducted during the project feasibility study stage to ensure the synergistic and integrated effects of project groups. Current feasibility study stages for power grid renovation projects have many limitations in management and evaluation methods, especially regarding the collaborative management of project groups and the comprehensive analysis of multi-dimensional data, lacking systematic and in-depth integration and processing.

[0003] In related technologies, on the one hand, in traditional power grid renovation project management, semantic data extraction typically focuses only on the frequency of single keywords or simple labeling, making it difficult to accurately capture the correlation between projects and failing to effectively tap into their collaborative potential. On the other hand, the geographical information of power grid projects is closely related to the power grid topology; however, in existing project management, geographical data and power grid topology are often viewed separately, leading to uneven resource allocation among multiple projects within the same geographical area, resulting in wasted resources and delays in project progress. At the temporal level, the lack of quantitative analysis on project schedule dependencies and timeline connections leads to a disconnect in project construction rhythms.

[0004] However, with the use of existing technologies, the evaluation of project clusters lacks comprehensiveness, and the identification of key project clusters is inaccurate, which seriously restricts the overall progress efficiency and investment benefits of power grid transformation projects. Summary of the Invention

[0005] The embodiments described herein provide a method, apparatus, and medium for comprehensive evaluation of project portfolios for power grid transformation projects, overcoming the aforementioned problems.

[0006] Firstly, based on the content of this disclosure, a comprehensive evaluation method for project clusters of power grid renovation projects is provided, including: Acquire relevant textual data, geographic information system data, project historical data, and power grid topology data related to power grid renovation projects; A semantic feature association network is constructed by extracting multi-dimensional semantic features and analyzing the correlation relationships of the relevant text data of the power grid renovation project; a geographic topology feature association network is constructed by performing spatial connection analysis on the geographic information system data and the power grid topology data; and a time-series feature association network is constructed by performing time-series feature analysis on the historical data of the project. Based on the semantic feature association network, the geographic topology feature association network, and the temporal feature association network, a multi-dimensional coupled network including semantic, geographic topology, and temporal features is constructed through graph computing and knowledge fusion. Identify core project groups with semantic similarity, geographic proximity, and temporal correlation from the multi-dimensional coupled network containing semantic-geographic topology-temporal information; A comprehensive evaluation model for the project group is established based on the core project group. The project group comprehensive evaluation model is used to comprehensively evaluate the project group to be evaluated, thereby obtaining a target project group with a high degree of synergy; and to assess the comprehensive benefits of the target project group in power grid transformation.

[0007] Secondly, according to the content of this disclosure, a comprehensive evaluation device for power grid renovation projects is provided, comprising: The acquisition module is used to acquire relevant text data, geographic information system data, project historical data, and power grid topology data for power grid renovation projects. The first construction module is used to construct a semantic feature association network by performing multi-dimensional semantic feature extraction and correlation analysis on the relevant text data of the power grid renovation project; to construct a geographic topology feature association network by performing spatial connection analysis on the geographic information system data and the power grid topology data; and to construct a time-series feature association network by performing time-series feature analysis on the historical data of the project. The second construction module is used to construct a multi-dimensional coupled network containing semantic, geographic topology, and temporal features based on the semantic feature association network, the geographic topology feature association network, and the temporal feature association network, through graph computing and knowledge fusion. The identification module is used to identify core project groups with semantic similarity, geographical proximity and temporal correlation from the multi-dimensional coupled network containing semantic-geographic topology-temporal data. A module is established to build a comprehensive evaluation model for the project group based on the core project group. The evaluation module is used to comprehensively evaluate the project group to be evaluated through the project group comprehensive evaluation model, to obtain the target project group with a high degree of synergy, and to evaluate the comprehensive benefits of the target project group in power grid transformation.

[0008] Thirdly, a computer device is provided, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the steps of the project group comprehensive evaluation method for power grid transformation projects as described in any of the above embodiments.

[0009] Fourthly, a computer-readable storage medium is provided, on which a computer program is stored, and when executed by a processor, the computer program implements the steps of the project group comprehensive evaluation method for power grid transformation projects as described in any of the above embodiments.

[0010] The method for comprehensive evaluation of project clusters for power grid renovation projects provided in this application involves acquiring relevant textual data, geographic information system (GIS) data, historical project data, and power grid topology data related to the power grid renovation projects. A semantic feature association network is constructed by extracting multi-dimensional semantic features and analyzing relationships in the relevant textual data. A geographic topology feature association network is constructed by performing spatial connectivity analysis on the GIS data and the power grid topology data. A temporal feature association network is constructed by performing temporal feature analysis on the historical project data. Based on the semantic feature association network, the geographic topology feature association network, and the temporal feature association network, a multi-dimensional coupled network including semantics, geographic topology, and temporal sequence is constructed through graph computing and knowledge fusion. Core project clusters with semantic similarity, geographic proximity, and temporal sequence correlation are identified from the multi-dimensional coupled network. A comprehensive evaluation model for the project clusters is established based on the core project clusters. The comprehensive evaluation model is used to comprehensively evaluate the project clusters to be evaluated, resulting in a target project cluster with a high degree of synergy. The overall benefits of the target project clusters in power grid renovation are then assessed. In this way, by integrating semantic data, geospatial data, and time-series data from the project feasibility study stage, a multi-dimensional coupled network can be constructed to accurately explore the synergistic effects of project clusters, effectively improve the comprehensiveness of project cluster evaluation, and thus enhance the overall progress efficiency and investment benefits of power grid transformation projects.

[0011] The above description is merely an overview of the technical solutions of the embodiments of this application. In order to better understand the technical means of the embodiments of this application and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of this application more obvious and understandable, specific implementation methods of this application are described below. Attached Figure Description

[0012] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments will be briefly described below. It should be understood that the drawings described below only relate to some embodiments of this disclosure and are not intended to limit this disclosure, wherein: Figure 1This is a flowchart illustrating a comprehensive evaluation method for power grid renovation projects.

[0013] Figure 2 This is a schematic diagram of the structure of a project group comprehensive evaluation device for power grid transformation projects provided in this disclosure.

[0014] Figure 3 This is a schematic diagram of the structure of a computer device provided in this disclosure.

[0015] It should be noted that the elements in the attached diagram are schematic and not drawn to scale. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the described embodiments of this disclosure without creative effort are also within the scope of protection of this disclosure.

[0017] Unless otherwise defined, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this subject matter pertains. It will be further understood that terms such as those defined in commonly used dictionaries shall be interpreted as having the meaning consistent with their meaning in the context of the specification and in the relevant art, and shall not be interpreted in an idealized or overly formal form unless otherwise explicitly defined herein. As used herein, the statement of “connecting” or “coupling” two or more parts together shall mean that these parts are directly joined together or joined through one or more intermediate components.

[0018] The term "embodiment" as used herein means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of the phrase "embodiment" in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0019] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists, A and B exist simultaneously, or B exists. Additionally, the character " / " generally indicates that the preceding and following related objects have an "or" relationship. Terms such as "first" and "second" are only used to distinguish one component (or part of a component) from another component (or another part of a component).

[0020] In the description of this application, unless otherwise stated, "multiple" means two or more (including two), and similarly, "multiple groups" means two or more (including two groups).

[0021] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0022] This disclosure aims to integrate multi-dimensional information such as semantics, time series, geography, and power grid topology to establish a dynamic project group evaluation model, which solves the problem of isolated multi-source information in power grid transformation projects. It can not only explore the inherent connections and synergistic effects between project groups, but also provide a more scientific basis for decision-making in power grid transformation projects.

[0023] Figure 1 This is a flowchart illustrating a comprehensive evaluation method for a power grid renovation project portfolio provided in this embodiment of the disclosure. Figure 1 As shown, the specific process of the comprehensive evaluation method for power grid renovation projects includes: S110. Obtain relevant text data, geographic information system data, project historical data, and power grid topology data for power grid renovation projects.

[0024] The goal of the data collection phase is to acquire multi-source heterogeneous data related to power grid infrastructure and renovation projects, namely, relevant text data, geographic information system data, project historical data, and power grid topology data.

[0025] In some embodiments, acquiring relevant textual data, geographic information system data, historical project data, and power grid topology data related to power grid renovation projects includes: Feasibility study reports and management documents related to the power grid renovation project are obtained from project management platforms, electronic archives, and contract management systems; geographic information system (GIS) data is obtained from power grid operation management systems, GIS data platforms, or other relevant geographic data storage systems; historical project data is obtained from project management systems, construction progress tracking tools, and historical investment return systems; power grid topology data is extracted from power dispatching systems, data acquisition and monitoring systems, and power grid modeling systems; and the collected text data, GIS data, historical project data, and power grid topology data related to the power grid renovation project are preprocessed by data cleaning, format unification, and standardization.

[0026] Both the feasibility study report and management documents are text-based data. The feasibility study report provides information such as the project's basic information, construction objectives, technical solutions, and investment budget. Management documents, such as project plans, progress reports, technical specifications, and quality assessment reports, describe data related to management, quality control, and schedule management during project implementation.

[0027] Geographic Information System (GIS) data includes geographical locations, power supply areas, line locations, and equipment layout information related to power grid upgrade projects. For example, the project's geographic coordinate data includes the latitude and longitude coordinates of power grid nodes (substations, distribution stations, etc.) and lines (transmission lines, distribution lines, etc.). Geographic boundary data includes boundary information for the power supply area, which may involve natural obstacles such as terrain, landforms, rivers, and mountains. Infrastructure data includes the locations of roads, transportation networks, and buildings. Line locations include the starting and ending points of transmission lines, as well as the locations of key intermediate nodes. Equipment layout information includes the specific location arrangements of facilities such as transformers, switchgear, and control rooms within substations.

[0028] Project historical data includes past project execution records and project effectiveness evaluations. This includes historical project progress, construction schedule, completion milestones, and any changes that have occurred. Power grid topology data includes power grid node data and connection relationship data. For example, power grid node data includes detailed information such as equipment number, type, function, and capacity of equipment like substations, power supply areas, circuit breakers, and switching stations. Connection relationship data describes the connections between power transmission lines and communication lines between various nodes in the power grid, including line length, capacity, operating voltage, and load.

[0029] During preprocessing, data cleaning tasks may include: checking all data tables and files for missing fields or incomplete records. For missing values, imputation can be performed using interpolation, regression, or other methods, or reasonable inferences can be made based on the project's background. For example, for missing commissioning times in historical data, estimations can be made using commissioning times of similar projects. Correcting data entered incorrectly due to formatting errors, logical errors, or obvious inconsistencies, such as project initiation times being later than commissioning times or inconsistent power supply area data. Checking for duplicate records across different data sources. For example, the same power grid node may appear multiple times in different data tables; removing duplicate records reduces the impact of redundant data. Format unification and standardization include unifying data field naming and types, units, and time formats. For example, "voltage" can be uniformly named "voltage," and "capacity" can be uniformly named "capacity." All date fields should be standardized to the "YYYY-MM-DD" format, and numerical data should be standardized to floating-point numbers. For data involving different units (such as power load units potentially being kW or MW), uniform unit conversion should be performed to ensure data comparisons are conducted within the same unit. All geographic data uses a unified coordinate system (such as WGS84 or UTM) for subsequent spatial analysis. Project time-series data may involve different time intervals; for example, some projects may have construction periods of several months, while others may have periods of several years. All times can be converted to relative times according to the project's start and end dates. Data that has been cleaned, formatted, and standardized can be stored in a relational database or graph database. For continuously updated data, a version control mechanism can be used to ensure that historical versions of the data can be traced and managed.

[0030] S120. By extracting multi-dimensional semantic features and analyzing the correlation between relevant text data of power grid renovation projects, a semantic feature association network is constructed; by performing spatial connection analysis on geographic information system data and power grid topology data, a geographic topology feature association network is constructed; by performing temporal feature analysis on historical project data, a temporal feature association network is constructed.

[0031] In some embodiments, a semantic feature association network is constructed by extracting multi-dimensional semantic features and analyzing the correlation relationships of relevant text data of power grid renovation projects. This includes: extracting multi-dimensional semantic features from relevant text data of power grid renovation projects using natural language processing and / or text mining techniques; analyzing the semantic correlation relationships between various semantic features in the multi-dimensional semantic features; and constructing a semantic feature association network by using semantic features as network nodes and the semantic correlation relationships between various semantic features as edges.

[0032] The semantic feature association network focuses primarily on the processing and analysis of text data. Key semantic features (i.e., multi-dimensional semantic features) can be extracted from project-related documents using natural language processing and text mining techniques, such as project objectives, task descriptions, technical specifications, timelines, and responsible parties. Semantic relationships are identified by calculating the semantic similarity between features, such as "depends on," "contains," and "belongs to." Semantic features are used as nodes, and the semantic relationships between nodes are used as edges to construct the semantic feature association network. The semantic similarity can be calculated using cosine similarity, as shown in formula (1).

[0033] (1) In formula (1), cos( () represents the semantic similarity value; It is the angle between two semantic features; x and y represent the two semantic features respectively, x i and y i These represent the feature values ​​in the i-th dimension of the corresponding semantic features. A semantic similarity threshold is set; when the semantic similarity between two semantic features is higher than this threshold, they are considered to have a direct semantic relationship.

[0034] Different semantic relationship types can be represented by different edges, such as "influence," "dependency," and "similarity." For example, an edge between a "target" node and a "technical requirement" node represents a dependency, while an edge between two similar "project target" nodes represents similarity. Graph databases (such as Neo4j and ArangoDB) can be used to store the metadata, attribute information, and relationships of each node and edge as graph data. By graphically displaying the semantic feature association network, nodes and edges can be colored, labeled, or resized according to different attributes, facilitating the rapid identification of key nodes and semantic relationships.

[0035] Therefore, in the semantic dimension, technologies such as natural language processing and text mining are used to extract multi-dimensional semantic features from textual materials such as project management documents, such as identifying semantic information like project goals and technical specifications. Simultaneously, by analyzing relationships through semantic similarity calculation and knowledge graph construction, semantic features are presented as network nodes, and relationships are used as edges, constructing a multi-dimensional semantic feature association network. This clearly reveals the semantic logic of the project and aids in understanding the project's inherent business relationships.

[0036] In some embodiments, a geographic topology feature association network is constructed by performing spatial connectivity analysis on geographic information system data and power grid topology data, including: extracting the project's geographical location and the line connection relationships in geographic space from the geographic information system data and power grid topology data; and constructing a geographic topology feature association network with the project's geographical location as network nodes and the line connection relationships in geographic space as edges.

[0037] This involves extracting information such as the project's geographical coordinates, power supply area, and line connection relationships based on GIS data and power grid topology data, and constructing a geospatial association network. Specifically, through methods such as spatial distance calculation and topological connectivity analysis, a geographic topological feature association network is constructed with the project's geographical location as nodes and geographical connections, adjacencies, and radiation relationships as edges. This identifies the project's relationship with its geographical location and power grid structure, facilitating the analysis of the constraints and synergies of geographical factors on the project.

[0038] In some embodiments, a time-series feature association network is constructed by performing time-series feature analysis on historical project data. This includes: extracting project time features from historical project data using a time series analysis model, with time as the dimension. These project time features include: project initiation time, construction period, and commissioning time. Based on these project time features, the project time-series relationships are determined, including: time sequence, time parallelism, and time dependency. Each project is treated as a time-series node, and the project time-series relationships are treated as edges to construct a time-series feature association network.

[0039] The construction of the temporal feature association network is primarily aimed at analyzing the project's temporal progress, dependencies, and mutual influences. For the project's time dimension, a time series analysis model is used to extract the project's temporal features, including project initiation time, construction period, and production launch time. By treating projects as temporal nodes and relationships such as chronological order, parallelism, and dependencies as edges, a temporal feature association network is constructed. This network clearly demonstrates the project group's progress rhythm and mutual influences over time, providing support for controlling project temporal coordination.

[0040] S130. Based on semantic feature association network, geographic topology feature association network and temporal feature association network, a multi-dimensional coupled network including semantic, geographic topology and temporal features is constructed through graph computing and knowledge fusion.

[0041] In order to achieve a comprehensive analysis and understanding of the complex relationships among project groups, it is necessary to effectively match and integrate semantic feature association networks, geographic topological feature association networks, and temporal feature association networks.

[0042] In some embodiments, a multi-dimensional coupled network encompassing semantic, geographic topology, and temporal features is constructed based on semantic feature association networks, geographic topology feature association networks, and temporal feature association networks through graph computing and knowledge fusion. This includes: identifying node feature identifiers of project nodes in the semantic feature association network, geographic topology feature association network, and temporal feature association network respectively using graph computing algorithms; establishing node mapping relationships between corresponding nodes in different dimensional networks based on node feature identifiers using node matching algorithms; and performing entity alignment, relationship completion, and cross-fusion of the business logic of the semantic feature association network, the spatial association of the geographic topology feature association network, and the temporal relationship of the temporal feature association network based on the node mapping relationships to obtain a multi-dimensional coupled network encompassing semantic, geographic topology, and temporal features.

[0043] The feature identifiers include project codes, semantic tags, geographic coordinates, and time nodes. Project codes: unique across all networks, used to identify project nodes. Semantic tags: describe the nature, category, keywords, etc., of the project, such as "infrastructure construction" or "software development." Geographic coordinates: each project typically has a corresponding geographical location, represented by latitude and longitude coordinates. Time nodes: in a time-series network, the project's initiation date, construction period, and commissioning date can serve as time features.

[0044] Matching can be based on the similarity of node attributes or on the connection relationships between nodes. For example, in a semantic feature association network, whether a project's semantic label matches the time features in a temporal feature association network or the geographical location in a geographic topology feature association network can be determined by calculating similarity and weight values. In this way, the corresponding node for each project in three-dimensional space can be found, preparing for subsequent network fusion and making the multi-dimensional network more closely connected.

[0045] The purpose of entity alignment is to ensure that semantically identical or similar entities can be effectively matched across different networks. For example, in a semantic network, a project task might be labeled "power construction," while in a geographic network, the location of this project might be "City A," and in a time-series network, the time period might be "the first quarter of 2025." By understanding the semantics of entities, these three can be aligned, ensuring their effective integration within the network.

[0046] Relationship completion automatically fills in missing information or establishes new relationships by analyzing association rules in existing data. For example, some projects may have some relationships that are not explicitly labeled at the semantic level, and these relationships can be inferred and completed by analyzing temporal progress (such as some projects starting after a certain stage) or geographical spatial proximity.

[0047] Knowledge graph fusion and graph convolutional networks (GCNs) can be used to cross-integrate information from the three networks. Specifically, a weighted graph can be constructed, assigning different weights to information from different dimensions. Through weighted fusion, a unified multi-dimensional coupled network can be formed to eliminate information redundancy and conflict, creating a network coupling model that comprehensively covers the semantic, geographical, and temporal characteristics of the project, with each dimension of information complementing and relating to each other, thus comprehensively depicting the complex relationships of the project group.

[0048] S140. Identify core project groups with semantic similarity, geographical proximity and temporal correlation from a multi-dimensional coupled network containing semantic-geographic topology-temporal sequence.

[0049] In this multi-dimensional coupled network of semantic-geographic topology-temporal sequence, each node represents a project, and the connections between nodes represent certain associations between projects. The strength or nature of these associations can be semantic similarity, spatial proximity, or temporal relationships. Specialized coupled project cluster mining algorithms can be developed using the constructed multi-dimensional coupled network. The core of the project cluster mining algorithm lies in identifying project clusters with high semantic similarity, geographical proximity, and temporal correlation based on the association strength of nodes in the network and the network structure characteristics.

[0050] In some embodiments, identifying core item groups with semantic similarity, geographical proximity, and temporal correlation from a multi-dimensional coupled network containing semantic-geographic topology and temporal sequence includes: calculating the semantic correlation strength, geographical correlation strength, and temporal correlation strength between network nodes in the multi-dimensional coupled network; determining item groups with high semantic similarity, geographical proximity, and temporal correlation based on the semantic correlation strength, geographical correlation strength, and temporal correlation strength between network nodes in the multi-dimensional coupled network; optimizing the partitioning results of the item groups; and determining core item groups with semantic similarity, geographical proximity, and temporal correlation based on the synergistic benefits of each item group within the item group.

[0051] Specifically, the strength of semantic association can be assessed by calculating the similarity between semantic tags or attributes of projects. The strength of geographic association can be assessed by calculating the spatial location relationships of projects. The strength of temporal association can be assessed by analyzing the time schedule and temporal dependencies of projects.

[0052] To optimize the project clustering results, threshold and weight parameters are set. The threshold determines which relationships are strong enough to group projects into the same cluster, while the weight parameters adjust the importance of each dimension. By setting thresholds and weight parameters, the project clustering results are optimized, identifying project clusters that have a key impact on the overall progress and synergistic benefits of power grid renovation projects. This focuses on the core set of related projects, narrowing the analysis scope for subsequent comprehensive evaluation. For example, projects can be divided into several groups based on the strength of their relationships. A weighted K-means algorithm can then be used to incorporate the weight of each dimension into the clustering calculation. Alternatively, a hierarchical tree can be constructed to divide project clusters, merging projects layer by layer based on the strength of their relationships, ultimately forming a tree structure where each leaf node represents a project cluster.

[0053] After obtaining the initial project cluster division results, the results are optimized using a multi-objective optimization algorithm based on the synergistic benefits of each project cluster, identifying the core project clusters. Core project clusters are those that have a critical impact on the overall progress and synergistic benefits of the power grid renovation project clusters. For example, projects within a cluster may share resources, technology, or time; these projects should be grouped together as much as possible. Simultaneously considering the multi-objective optimization problem across semantic, geographical, and temporal dimensions, multi-objective optimization algorithms (such as genetic algorithms and particle swarm optimization) are used to optimize the project cluster division.

[0054] S150. Establish a comprehensive evaluation model for the project group based on the core project group; conduct a comprehensive evaluation of the project group to be evaluated through the comprehensive evaluation model to obtain a target project group with a high degree of synergy; and evaluate the comprehensive benefits of the target project group in power grid transformation.

[0055] This involves developing a series of business rules tailored to the specific characteristics of power grid upgrade projects. These rules can be based on industry experience, key success factors in project implementation, and risk prevention requirements. For example, project groups can be prioritized based on their importance, urgency, or impact on power grid upgrades. If a project is crucial to the overall power grid upgrade, its score should be given a higher weight in the comprehensive evaluation. Potential risks within the project group, such as technical, financial, and policy risks, should be assessed, and risk thresholds should be set to ensure these risk factors are reasonably reflected in the comprehensive evaluation.

[0056] After constructing a comprehensive evaluation model for project clusters, the comprehensive evaluation methods of the project cluster comprehensive evaluation model can be used to identify target project clusters with high synergistic effects, evaluate their comprehensive benefits in power grid transformation, and provide quantitative and comprehensive evaluation results for project feasibility study decisions.

[0057] In some embodiments, a comprehensive evaluation model for the project group is established based on the core project group, including: constructing an initial evaluation model by using semantic similarity, geographical proximity, and temporal correlation as project evaluation indicators; and refining the initial evaluation model through business rules and actual project needs to obtain a comprehensive evaluation model for the project group.

[0058] This process transforms indicators such as semantic similarity, geographical proximity, and temporal correlation into quantifiable features and combines them with machine learning methods for modeling. The model is trained based on historical project data and labeled evaluation results. The training process includes: Dataset partitioning: Dividing the project cluster dataset into training, validation, and test sets for model training, parameter tuning, and final validation. Cross-validation: Ensuring the model's generalization ability, i.e., its ability to effectively predict unknown data, through cross-validation. Performance evaluation: Evaluating the model's performance using metrics such as accuracy, recall, and F1 score to ensure high predictive power. After training and validation of the project cluster comprehensive evaluation model, the model can quantitatively evaluate the synergistic effect of each project cluster and identify project clusters with high synergistic effects.

[0059] In this embodiment, relevant textual data, geographic information system (GIS) data, historical project data, and power grid topology data of the power grid renovation project are acquired. A semantic feature association network is constructed by extracting multi-dimensional semantic features and analyzing relationships in the relevant textual data. A geographic topology feature association network is constructed by performing spatial connectivity analysis on the GIS data and power grid topology data. A temporal feature association network is constructed by performing temporal feature analysis on the historical project data. Based on the semantic feature association network, geographic topology feature association network, and temporal feature association network, a multi-dimensional coupled network including semantics, geographic topology, and temporal sequence is constructed through graph computing and knowledge fusion. Core project groups with semantic similarity, geographic proximity, and temporal sequence correlation are identified from the multi-dimensional coupled network. A comprehensive evaluation model for the project groups is established based on the core project groups. The comprehensive evaluation model is used to comprehensively evaluate the project groups to be evaluated, resulting in a target project group with a high degree of synergy. The comprehensive benefits of the target project group in the power grid renovation are then assessed. In this way, by integrating semantic data, geospatial data, and time-series data from the project feasibility study stage, a multi-dimensional coupled network can be constructed to accurately explore the synergistic effects of project clusters, effectively improve the comprehensiveness of project cluster evaluation, and thus enhance the overall progress efficiency and investment benefits of power grid transformation projects.

[0060] In summary, this embodiment addresses the problem of isolated multi-source information by constructing a network model that integrates semantic, temporal, and geographical multi-dimensional information with the power grid's physical topology. It also facilitates a paradigm shift from static, isolated project evaluation to dynamic, interconnected intelligent mining of project clusters. Specifically, by integrating semantic, geographical, temporal, and power grid topology information, it comprehensively and deeply mines the intrinsic connections and synergistic relationships between project clusters. Simultaneously, by combining graph computing and knowledge fusion technologies, it deeply mines the complex relationships and dynamic patterns inherent in the multi-dimensional data between projects, ultimately identifying project clusters with high synergistic effects. Furthermore, during the project cluster evaluation process, it fully considers the semantic relationships, temporal relationships, and power grid topology information of the projects, constructing a comprehensive project evaluation system. This improves the accuracy and comprehensiveness of the overall project cluster evaluation, providing more scientific, detailed, and practical decision-making basis for power grid transformation project feasibility studies, better adapting to the complex needs of power grid transformation projects, and achieving better investment planning and project decisions.

[0061] In terms of data utilization, existing technologies largely rely on static indicators or abstract relational networks, failing to effectively integrate multi-source heterogeneous information about projects. This embodiment constructs a semantic-geographic topology-temporal multi-dimensional coupled network, achieving deep integration of the semantic connotation of project texts, spatial geographic distribution, temporal evolution patterns, and the physical topology of the power grid. This solves the problem of information silos and provides a more comprehensive, three-dimensional, and accurate data foundation for comprehensive project evaluation. Regarding relational mining, existing technologies are either limited to predefined logical relationships or neglect spatiotemporal dynamic characteristics. This embodiment introduces graph computing and knowledge fusion technologies into the field of power grid project evaluation, enabling the autonomous mining of potential multi-dimensional dynamic relationships between projects from raw data. This not only enhances the objectivity and automation of relational analysis but also realizes a shift from static attribute evaluation to dynamic relationship mining, significantly improving the ability to identify synergistic effects between projects. In terms of project evaluation methods, existing technologies often score and rank isolated projects, making it difficult to identify group synergistic effects. This embodiment uses multi-network fusion analysis and coupled project group mining algorithms to evaluate the "project group" as a whole. It can accurately identify project combinations with high synergy in function, time and space and topology, providing more scientific and insightful support for the group optimization, resource coordination and investment decision-making of power grid transformation projects.

[0062] Figure 2 This is a schematic diagram of a project group comprehensive evaluation device for power grid renovation projects provided in this embodiment. The project group comprehensive evaluation device for power grid renovation projects may include: The acquisition module 210 is used to acquire relevant text data, geographic information system data, project historical data, and power grid topology data related to the power grid renovation project.

[0063] The first construction module 220 is used to construct a semantic feature association network by extracting multi-dimensional semantic features and analyzing the correlation between relevant text data of power grid transformation projects; to construct a geographic topology feature association network by performing spatial connection analysis on geographic information system data and power grid topology data; and to construct a time-series feature association network by performing time-series feature analysis on historical data of projects.

[0064] The second construction module 230 is used to construct a multi-dimensional coupled network containing semantic, geographic topology, and temporal features based on semantic feature association network, geographic topology feature association network, and temporal feature association network, through graph computing and knowledge fusion.

[0065] The identification module 240 is used to identify core project groups with semantic similarity, geographical proximity and temporal correlation from a multi-dimensional coupled network containing semantic-geographic topology-temporal sequence.

[0066] Module 250 is established to create a comprehensive evaluation model for project groups based on the core project group.

[0067] Evaluation module 260 is used to comprehensively evaluate the project group to be evaluated through the project group comprehensive evaluation model, to obtain the target project group with high synergy effect, and to evaluate the comprehensive benefits of the target project group in power grid transformation.

[0068] In this embodiment, optionally, the second building module 230 is specifically used for: Graph computing algorithms are used to identify the node feature identifiers of project nodes in semantic feature association networks, geographic topology feature association networks, and temporal feature association networks. The feature identifiers include project codes, semantic labels, geographic coordinates, and time nodes. Based on the node feature identifiers, node mapping relationships between corresponding nodes in different dimensional networks are established through node matching algorithms. Based on the node mapping relationships, entity alignment, relationship completion, and cross-fusion are performed on the business logic of the semantic feature association network, the spatial association of the geographic topology feature association network, and the temporal relationship of the temporal feature association network to obtain a multi-dimensional coupled network containing semantic, geographic topology, and temporal features.

[0069] In this embodiment, optionally, the identification module 240 is specifically used for: Calculate the semantic association strength, geographical association strength, and temporal association strength among network nodes in a multidimensional coupled network; based on the semantic association strength, geographical association strength, and temporal association strength among network nodes in the multidimensional coupled network, identify project groups with high semantic similarity, geographical proximity, and temporal association; optimize the project group partitioning results; and based on the synergistic benefits of each project group, identify core project groups with semantic similarity, geographical proximity, and temporal association.

[0070] In this embodiment, optionally, the establishment module 250 is specifically used for: Semantic similarity, geographical proximity, and temporal correlation are used as project evaluation indicators to construct an initial evaluation model. The initial evaluation model is then modified based on business rules and actual project needs to obtain a comprehensive evaluation model for the project group.

[0071] In this embodiment, optionally, the first construction module 220 is specifically used for: Multi-dimensional semantic features are extracted from relevant text data of power grid renovation projects using natural language processing and / or text mining techniques; the semantic relationships between various semantic features are analyzed; and a semantic feature association network is constructed by using semantic features as network nodes and the semantic relationships between various semantic features as edges.

[0072] In this embodiment, optionally, the first construction module 220 is specifically used for: Extract the project's geographical location and geospatial line connections from geographic information system data and power grid topology data; construct a geographic topology feature association network with the project's geographical location as network nodes and geospatial line connections as edges.

[0073] In this embodiment, optionally, the first construction module 220 is specifically used for: Using a time series analysis model, project time features are extracted from historical project data with time as the dimension. These features include project initiation time, construction period, and commissioning time. Based on these time features, project time sequence relationships are determined, including sequential, parallel, and dependent relationships. Each project is treated as a time sequence node, and the project time sequence relationships are treated as edges, thus constructing a time sequence feature association network.

[0074] In this embodiment, optionally, the acquisition module 210 is specifically used for: Feasibility study reports and management documents related to the power grid renovation project are obtained from project management platforms, electronic archives, and contract management systems; geographic information system (GIS) data, including geographical locations, power supply areas, line locations, and equipment layout information, is obtained from power grid operation management systems, GIS data platforms, or other relevant geographic data storage systems; historical project data, including past project execution records and project effectiveness evaluations, is obtained from project management systems, construction progress tracking tools, and historical investment return systems; power grid topology data, including power grid node data and connection relationship data, is extracted from power dispatching systems, data acquisition and monitoring systems, and power grid modeling systems; and the collected text data, GIS data, historical project data, and power grid topology data related to the power grid renovation project are preprocessed by data cleaning, format unification, and standardization.

[0075] The project group comprehensive evaluation device for power grid transformation projects provided in this disclosure can execute the above-described method embodiments. Its specific implementation principle and technical effects can be found in the above-described method embodiments, and will not be repeated here.

[0076] This application also provides a computer device. Please refer to the following for details. Figure 3 , Figure 3 This is a basic structural block diagram of the computer device in this embodiment.

[0077] The computer device includes a memory 310 and a processor 320 that are interconnected via a system bus. It should be noted that only a computer device with memory 310 and processor 320 is shown in the figure; however, it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented alternatively. Those skilled in the art will understand that the computer device described herein is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0078] Computer devices can include desktop computers, laptops, handheld computers, and cloud servers. These devices allow for human-computer interaction with users through keyboards, mice, remote controls, touchpads, or voice-activated devices.

[0079] The memory 310 includes at least one type of readable storage medium, including non-volatile memory or volatile memory, such as flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. RAM may include static RAM or dynamic RAM. In some embodiments, the memory 310 may be an internal storage unit of a computer device, such as the hard disk or memory of the computer device. In other embodiments, the memory 310 may also be an external storage device of the computer device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, or flash card equipped on the computer device. Of course, the memory 310 may include both internal storage units and external storage devices of the computer device. In this embodiment, the memory 310 is typically used to store the operating system and various application software installed on the computer device, such as the program code of the method described above. In addition, the memory 310 can also be used to temporarily store various types of data that have been output or will be output.

[0080] Processor 320 is typically used to perform overall operations of a computer device. In this embodiment, memory 310 is used to store program code or instructions, including computer operation instructions, and processor 320 is used to execute the program code or instructions stored in memory 310 or process data, such as program code that runs the methods described above.

[0081] In this article, the bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus system can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0082] Another embodiment of this application also provides a computer-readable medium, which may be a computer-readable signal medium or a computer-readable medium. A processor in a computer reads computer-readable program code stored in the computer-readable medium, enabling the processor to execute the functional actions specified in each step or combination of steps in the above method; and to generate means for implementing the functional actions specified in each block or combination of blocks in the block diagram.

[0083] Computer-readable media include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared memory or semiconductor systems, devices or apparatuses, or any suitable combination thereof, wherein the memory is used to store program code or instructions, the program code including computer operation instructions, and the processor is used to execute the program code or instructions of the above-described methods stored in the memory.

[0084] The definitions of memory and processor can be found in the description of the foregoing computer device embodiments, and will not be repeated here.

[0085] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0086] In the various embodiments of this application, the functional units or modules can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0087] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0088] In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" as described in this application does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. This application can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims listing several means, several units of these means may be embodied by the same item of hardware. The use of "first," "second," and "third," etc., does not indicate any order and these words should be interpreted as names. Unless otherwise specified, the steps in the above embodiments should not be construed as limiting the order of execution.

[0089] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A comprehensive evaluation method for project clusters in power grid renovation projects, characterized in that, include: Acquire relevant textual data, geographic information system data, project historical data, and power grid topology data related to power grid renovation projects; A semantic feature association network is constructed by extracting multi-dimensional semantic features and analyzing the correlation relationships of the relevant text data of the power grid renovation project; a geographic topology feature association network is constructed by performing spatial connection analysis on the geographic information system data and the power grid topology data; and a time-series feature association network is constructed by performing time-series feature analysis on the historical data of the project. Based on the semantic feature association network, the geographic topology feature association network, and the temporal feature association network, a multi-dimensional coupled network including semantic, geographic topology, and temporal features is constructed through graph computing and knowledge fusion. Identify core project groups with semantic similarity, geographic proximity, and temporal correlation from the multi-dimensional coupled network containing semantic-geographic topology-temporal information; A comprehensive evaluation model for the project group is established based on the core project group. The project group comprehensive evaluation model is used to comprehensively evaluate the project group to be evaluated, thereby obtaining a target project group with a high degree of synergy; and to assess the comprehensive benefits of the target project group in power grid transformation.

2. The method according to claim 1, characterized in that, The method, based on the semantic feature association network, the geographic topology feature association network, and the temporal feature association network, constructs a multi-dimensional coupled network encompassing semantics, geographic topology, and temporal sequence through graph computation and knowledge fusion, including: The node feature identifiers of project nodes in the semantic feature association network, the geographic topology feature association network, and the temporal feature association network are identified by graph computing algorithms. The feature identifiers include project code, semantic label, geographic coordinates, and time node. Based on the node feature identifiers, a node mapping relationship between corresponding nodes in different dimensional networks is established through a node matching algorithm; Based on the node mapping relationship, the business logic of the semantic feature association network, the spatial association of the geographic topology feature association network, and the temporal relationship of the temporal feature association network are aligned, the relationship is completed, and cross-fused to obtain the multi-dimensional coupled network containing semantic, geographic topology, and temporal features.

3. The method according to claim 1, characterized in that, The identification of core project groups with semantic similarity, geographical proximity, and temporal correlation from the multi-dimensional coupled network encompassing semantic-geographical-temporal relationships includes: Calculate the semantic association strength, geographical association strength, and temporal association strength among the network nodes in the multi-dimensional coupled network; Based on the semantic association strength, geographical association strength, and temporal association strength among the network nodes in the multi-dimensional coupled network, project groups with high semantic similarity, geographical proximity, and temporal association are identified. The project groups are segmented and optimized; and based on the synergistic benefits of each project group within the project groups, the core project groups with semantic similarity, geographical proximity, and temporal correlation are determined.

4. The method according to claim 1, characterized in that, The establishment of a comprehensive evaluation model for the project group based on the core project group includes: Semantic similarity, geographical proximity, and temporal correlation are used as project evaluation indicators to construct an initial evaluation model. The initial evaluation model is then modified based on business rules and actual project needs to obtain the comprehensive evaluation model for the project group.

5. The method according to claim 1, characterized in that, The process involves extracting multi-dimensional semantic features and analyzing relationships from the relevant textual data of the power grid renovation project to construct a semantic feature association network, including: Multi-dimensional semantic features are extracted from the relevant text data of the power grid renovation project using natural language processing and / or text mining techniques; Analyze the semantic relationships between the semantic features in the multi-dimensional semantic features; By using the semantic features as network nodes and the semantic relationships between the semantic features as edges, the semantic feature association network is constructed.

6. The method according to claim 1, characterized in that, The step of constructing a geographic topology feature association network by performing spatial connectivity analysis on the geographic information system data and the power grid topology data includes: Extract the project's geographical location and geospatial line connections from the geographic information system data and the power grid topology data; Using the project's geographical location as network nodes and the line connections in the geographic space as edges, construct the geographic topology feature association network.

7. The method according to claim 1, characterized in that, The step of constructing a time-series feature association network by performing time-series feature analysis on the project's historical data includes: Using a time series analysis model, project time features are extracted from the project's historical data with time as the dimension. These project time features include: project initiation time, construction period, and commissioning time. The project time sequence relationship is determined based on the project time characteristics, and the project time sequence relationship includes: time sequence, time parallelism, and time dependency; Each project is treated as a time-series node, and the time-series relationships between the projects are treated as edges to construct the time-series feature association network.

8. The method according to claim 1, characterized in that, The acquisition of relevant text data, geographic information system data, historical project data, and power grid topology data for the power grid renovation project includes: Obtain feasibility study reports and management documents related to the power grid renovation project from the project management platform, electronic archives, and contract management system; Geographic information system (GIS) data is obtained from power grid operation and management systems, GIS data platforms, or other relevant geographic data storage systems. The GIS data includes geographic locations, power supply areas, line locations, and equipment layout information involved in the power grid renovation project. Historical project data is obtained from project management systems, construction progress tracking tools, and historical investment return systems. This historical project data includes past project execution records and project performance evaluations. Power grid topology data is extracted from power dispatching systems, data acquisition and monitoring systems, and power grid modeling systems. The power grid topology data includes power grid node data and connection relationship data. The collected text data, geographic information system data, historical project data, and power grid topology data related to the power grid renovation project are preprocessed by data cleaning, format unification, and standardization.

9. A comprehensive evaluation device for a group of projects for power grid renovation projects, characterized in that, include: The acquisition module is used to acquire relevant text data, geographic information system data, project historical data, and power grid topology data for power grid renovation projects. The first construction module is used to construct a semantic feature association network by performing multi-dimensional semantic feature extraction and correlation analysis on the relevant text data of the power grid renovation project; to construct a geographic topology feature association network by performing spatial connection analysis on the geographic information system data and the power grid topology data; and to construct a time-series feature association network by performing time-series feature analysis on the historical data of the project. The second construction module is used to construct a multi-dimensional coupled network containing semantic, geographic topology, and temporal features based on the semantic feature association network, the geographic topology feature association network, and the temporal feature association network, through graph computing and knowledge fusion. The identification module is used to identify core project groups with semantic similarity, geographical proximity and temporal correlation from the multi-dimensional coupled network containing semantic-geographic topology-temporal data. A module is established to build a comprehensive evaluation model for the project group based on the core project group. The evaluation module is used to comprehensively evaluate the project group to be evaluated through the project group comprehensive evaluation model, to obtain the target project group with a high degree of synergy, and to evaluate the comprehensive benefits of the target project group in power grid transformation.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the project group comprehensive evaluation method for power grid transformation projects as described in any one of claims 1 to 7.

Images