Task decision-making method for full life cycle of electric power project and related device

Abstract

The invention belongs to the technical field of electric power engineering, and relates to a task decision-making method for the full life cycle of an electric power project and a related device. According to the method, multi-source data of multiple participation units are acquired and preprocessed, key entities and association relationships are extracted, a power project domain knowledge graph is constructed, semantic retrieval and reasoning are performed on a target task based on the graph, related data and the association units are automatically matched, and then a standardized collaborative process is generated and executed. And finally, feeding back a processing result to the knowledge base to realize closed-loop management. According to the method, the multi-source data fusion capability and the task response precision are improved, cross-stage and cross-unit intelligent collaborative decision-making is realized, the problems of information isolated island and low decision-making efficiency are effectively solved, and the management intelligence level of the whole life cycle of an electric power project is remarkably improved.

Description

Technical Field

[0001] This invention belongs to the field of power engineering technology and relates to a task decision-making method and related devices for the entire life cycle of power projects. Background Technology

[0002] Power project construction is characterized by numerous participating entities, long cycles, diverse data sources, and complex cross-disciplinary collaboration, encompassing multiple phases including design, construction, operation, and maintenance. With the development of technologies such as BIM, big data, and knowledge graphs, an increasing number of digital tools are being applied to power engineering project management. Currently, some projects utilize collaborative platforms to share design drawings and progress information, or centrally store documents from each phase in databases to support phased task processing and information retrieval. These systems are typically built on relational databases, supporting structured data entry and simple retrieval, and some integrate workflow engines to automate approval processes.

[0003] However, due to the different data formats and standards used by participating units, and the fact that a large amount of key information exists in unstructured documents (such as text reports and drawing descriptions), the system struggles to automatically identify and associate effective information across stages and disciplines. When a new task is initiated, the system still relies on manual searching of historical data and determination of responsible units, resulting in serious information silos, low collaboration efficiency, and a lack of intelligent support for decision-making. This fails to meet the needs of efficient, accurate, and closed-loop task decision-making throughout the entire lifecycle of power projects. Summary of the Invention

[0004] To address the problems in existing technologies, this invention provides a task decision-making method and related apparatus for the entire lifecycle of power projects, which significantly improves cross-unit collaboration efficiency and the level of intelligence in task decision-making.

[0005] To achieve the above objectives, the present invention employs the following technical solution: In a first aspect, the present invention provides a task decision-making method for the entire life cycle of power projects, comprising the following steps: Acquire multi-source data from multiple participating units in the power project, and preprocess the multi-source data; Based on preprocessed multi-source data, key entities and relationships in the multi-source data are extracted and structured. The processed structured data is associated with and stored in the collaborative design knowledge base along with the unstructured source data. Based on the structured data in the collaborative design knowledge base, a knowledge graph for the power project domain is constructed. The target design task is obtained, and semantic retrieval and reasoning are performed on the target design task based on the knowledge graph. Relevant multi-source data is automatically matched and pushed from the collaborative design knowledge base, and related participating units are pushed out based on the knowledge graph. Based on the pushed information, a standardized collaborative workflow is generated, the collaborative workflow is executed, and the final processing result generated by the execution is returned as new multi-source data and stored in the collaborative design knowledge base to achieve closed-loop management of task decision-making.

[0006] Preferably, the multi-source data includes: BIM model data, CAD drawings, and design calculation sheets from the design unit; project progress reports and change orders from the construction unit; on-site acceptance records and material testing reports from the construction unit; equipment operating parameters and fault reporting records from the operation unit; and geological survey data, meteorological monitoring data, and industry regulations and standards provided by third parties.

[0007] Preferably, the method for preprocessing the multi-source data includes: S1. Identify and correct outliers, missing values, and format errors in the multi-source data; S2. Data from different participating units and in different formats are uniformly converted and mapped according to the preset power project data standards; S3. De-identify and encrypt fields involving trade secrets or personal privacy; S4. Assign unified project identifiers, stage identifiers, and professional identifiers to the processed data to support subsequent associated storage and traceability.

[0008] Preferably, the method for extracting and structuring key entities and relationships in multi-source data includes: Based on a predefined entity dictionary and rule template for the power project domain, key entities are identified and extracted from preprocessed multi-source data. The key entities include at least project participants, equipment and facilities, design parameters, technical issues, specification clauses, and geographical locations. Based on the key entities, the contextual semantics are analyzed using a natural language processing model, and the relationships between the key entities are extracted according to the preset relationship types. The extracted key entities and relationships are organized and stored using a unified structured data model for constructing the knowledge graph.

[0009] Preferably, the method for semantic retrieval and reasoning of the target design task based on the knowledge graph includes: Analyze the task requirements of the target design task and identify the key entities within them; Using the key entities as query nodes, semantic expansion and path traversal are performed in the knowledge graph to retrieve related entities and relationships; Based on the search results and preset reasoning rules, multi-source data and associated participating units related to the target design task are pushed out.

[0010] Preferably, the method for generating standardized collaborative workflows includes: Based on the associated participating units in the push notification, the entity responsible for executing the process is determined; Based on the relevant multi-source data from the push notification, the input data and output requirements of each execution entity are clearly defined; Based on the input data and output requirements, a standardized workflow containing task sequences, execution standards, and time nodes is generated through a preset power project collaborative work template.

[0011] Preferably, the method of returning the final processing result generated by the execution as new multi-source data and storing it in the collaborative design knowledge base includes: The final processing result is then subjected to quality verification and version marking. Associate the verified results with the corresponding project identifier, task identifier, and processing unit identifier; The results after association and identification are stored in the collaborative design knowledge base according to a preset format, and the corresponding entities and relationships in the knowledge graph are updated.

[0012] Secondly, the present invention provides a task decision-making system for the entire lifecycle of power projects, comprising: Data acquisition module: used to acquire multi-source data from multiple participating units in the power project and to preprocess the multi-source data; Entity Relationship Extraction Module: Used to extract and structure key entities and relationships from preprocessed multi-source data; Knowledge storage management module: used to associate and store the processed structured data with the unstructured source data in the collaborative design knowledge base; Knowledge graph construction module: used to construct a knowledge graph for the power project domain based on the structured data in the collaborative design knowledge base; Retrieval and Reasoning Module: Used to obtain the target design task, perform semantic retrieval and reasoning on the target design task based on the knowledge graph, automatically match and push relevant multi-source data from the collaborative design knowledge base, and infer the associated participating units based on the knowledge graph; Process generation and execution module: Based on the pushed information, it generates a standardized collaborative workflow, executes the collaborative workflow, and returns the final processing result as new multi-source data to the collaborative design knowledge base to achieve closed-loop management of task decision-making.

[0013] Thirdly, the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement steps of a task decision-making method for the entire life cycle of a power project.

[0014] Fourthly, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of a task decision-making method oriented towards the entire life cycle of a power project.

[0015] Compared with the prior art, the present invention has the following beneficial effects: This invention integrates multi-source heterogeneous data from multiple units and stages, performs unified preprocessing and structured modeling, and constructs a knowledge graph for the power industry. This enables semantic understanding and intelligent reasoning regarding task requirements. Based on this, it automatically matches relevant data with responsible units, generates and executes standardized collaborative processes, and finally feeds the results back to update the knowledge base, forming a closed-loop mechanism. Because it achieves full-chain automation from data integration to knowledge-driven processes to process implementation, it solves the problems of severe information silos, low efficiency of manual matching, and difficulty in reusing experience in traditional models. It also improves the intelligence level of task decision-making, enhances cross-unit collaborative efficiency, and ensures the continuous accumulation of project knowledge. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0019] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0020] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0021] In the description of the embodiments of the present invention, it should be noted that if terms such as "upper," "lower," "horizontal," or "inner" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of the invention is in use, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. Furthermore, terms such as "first" and "second" are only used to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0022] Furthermore, the use of the term "horizontal" does not imply that the component must be absolutely horizontal, but rather that it can be slightly tilted. For example, "horizontal" simply means that its direction is more horizontal than "vertical," and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0023] In the description of the embodiments of the present invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention according to the specific circumstances.

[0024] The present invention will now be described in further detail with reference to the accompanying drawings: The first objective of this invention is to provide a task decision-making method for the entire lifecycle of power projects, such as... Figure 1 As shown, it includes the following steps: Acquire multi-source data from multiple participating units in the power project, and preprocess the multi-source data; Based on preprocessed multi-source data, key entities and relationships in the multi-source data are extracted and structured. The processed structured data is associated with and stored in the collaborative design knowledge base along with the unstructured source data. Based on the structured data in the collaborative design knowledge base, a knowledge graph for the power project domain is constructed. The target design task is obtained, and semantic retrieval and reasoning are performed on the target design task based on the knowledge graph. Relevant multi-source data is automatically matched and pushed from the collaborative design knowledge base, and related participating units are pushed out based on the knowledge graph. Based on the pushed information, a standardized collaborative workflow is generated, the collaborative workflow is executed, and the final processing result generated by the execution is returned as new multi-source data and stored in the collaborative design knowledge base to achieve closed-loop management of task decision-making.

[0025] This invention employs a unified data preprocessing mechanism to clean, standardize, and label heterogeneous data from different participants, ensuring data consistency and traceability. Subsequently, it utilizes a combination of natural language processing and a rule engine to extract key entities (such as equipment, technical issues, and regulatory clauses) and their relationships from unstructured text and semi-structured data, organizing them into a structured data model. This structured information, along with the original unstructured data (such as PDF documents and 3D model files), is linked using unique identifiers and jointly stored in a collaborative design knowledge base, forming a two-layer "data-knowledge" architecture. Based on this, graph database technology is used to construct a knowledge base for power projects. A dedicated knowledge graph enables semantic links between multi-dimensional entities. When receiving specific design task requirements, the system can parse the task semantics, locate core entities, and perform path expansion and neighborhood search in the knowledge graph to uncover highly relevant technical materials, historical cases, and entities that have participated in similar work. Furthermore, based on the matched data resources and collaborating units, a standardized collaborative process is automatically generated, including task division, input and output definitions, time nodes, and execution standards. The results generated after the process is executed undergo quality verification and version control, and are then fed back into the knowledge base to update the node and edge relationships in the knowledge graph, forming a continuously evolving knowledge loop.

[0026] The multi-source data includes: BIM model data, CAD drawings, and design calculation sheets from the design unit; project progress reports and change orders from the construction unit; on-site acceptance records and material testing reports from the construction unit; equipment operating parameters and fault reporting records from the operation unit; and geological survey data, meteorological monitoring data, and industry regulations and standards provided by third parties.

[0027] Specifically, the BIM (Building Information Modeling) model data provided by the design unit is a three-dimensional digital design outcome, containing equipment geometric information, system topology relationships, and attribute parameters, which can be used to support visual collaborative design and clash detection; CAD (Computer-Aided Design) drawings are two-dimensional engineering drawings, widely used in professional design expressions such as electrical main wiring and civil engineering layout; design calculation sheets record the calculation process and results of key technologies such as short-circuit current, load capacity, and stability analysis, and are an important basis for the compliance and safety of the design scheme. The project progress report provided by the construction unit reflects the actual progress of the project, including planned completion, actual completion, and analysis of reasons for delays, and is used to dynamically track the project execution pace; change orders record adjustments to the design or construction content caused by design optimization, changes in site conditions, etc., involving the division of responsibilities and cost changes, and are important legal and technical documents in project management. The on-site acceptance records submitted by the construction unit are confirmation documents of the completed quality of each sub-item of the project, including information such as the acceptance time, location, and standard compliance judgment, ensuring that the quality of the construction process is controllable. Material testing reports are issued by third-party testing institutions, testing and verifying the physical and electrical properties of key building materials such as steel bars, cables, and insulators to ensure that the materials meet national or industry standards. Real-time monitoring data of equipment operating parameters generated by the operating unit, such as voltage, current, temperature, and vibration, reflects the in-service status of power equipment and can be used for health assessment and trend prediction. Fault reporting records document the time, location, description of the phenomenon, handling measures, and recovery status of equipment anomalies, forming a typical fault case library to support intelligent diagnosis and preventative maintenance recommendations based on historical experience.

[0028] Furthermore, third-party geological survey data reveals geographical environmental characteristics such as the bearing capacity of substations and transmission line corridors, the distribution of soil and rock layers, and groundwater levels, influencing foundation design selection. Meteorological monitoring data, including regional climate information such as wind speed, icing thickness, and lightning activity frequency, is used to verify the wind resistance, anti-icing, and lightning withstand performance of transmission lines. Industry regulations and specifications cover national standards (such as the GB series), power industry standards (such as the DL / T series), and internal technical guidelines of enterprises, providing unified technical standards and compliance basis for design, construction, and operation and maintenance. Although such external data is not generated by the project entity, it has a decisive impact on the safety and adaptability of the project.

[0029] For example, a method for preprocessing the multi-source data includes: S1. Identify and correct outliers, missing values, and format errors in the multi-source data; S2. Data from different participating units and in different formats are uniformly converted and mapped according to the preset power project data standards; S3. De-identify and encrypt fields involving trade secrets or personal privacy; S4. Assign unified project identifiers, stage identifiers, and professional identifiers to the processed data to support subsequent associated storage and traceability.

[0030] This invention significantly improves the quality of raw data and reduces noise interference by identifying and correcting outliers, missing values, and format errors; it eliminates semantic ambiguity and technical barriers by completing cross-format and cross-unit data mapping under a unified data standard; it ensures the security and compliance of data during the flow process by de-identifying and encrypting sensitive fields; and it supports refined data management and full-link tracking by establishing a three-dimensional identification system that includes projects, stages, and professions.

[0031] For example, the method for extracting and structuring key entities and relationships in multi-source data includes: Based on a predefined entity dictionary and rule templates for the power project domain, key entities are identified and extracted from preprocessed multi-source data. These key entities include at least project participants, equipment and facilities, design parameters, technical issues, regulatory clauses, and geographical locations. Firstly, the entity dictionary and rule templates for the power project domain, built based on expert experience, are used to quickly locate and identify key entities with clear semantic boundaries in unstructured text or semi-structured documents. For example, the entity dictionary may contain professional terms such as "substation," "transmission line," "transformer capacity," and "insulation class," while the rule templates can be used to match typical phrases such as "a certain piece of equipment malfunctioned due to overload," thereby accurately extracting "equipment," "technical issues," and their attribute values.

[0032] Based on the key entities, the contextual semantics are analyzed using a natural language processing model, and the relationships between the key entities are extracted according to the preset relationship types. The natural language processing model used can be a sequence labeling and relationship classification model fine-tuned based on a pre-trained language model (such as BERT or RoBERTa), or it can be combined with dependency parsing or graph neural network technology to capture the potential semantic connections between entities across multiple sentences.

[0033] The extracted key entities and relationships are organized and stored using a unified structured data model to construct the knowledge graph. This structured data model typically adopts a graph data model, where nodes represent entities, edges represent relationships, and corresponding attribute fields (such as timestamps, confidence levels, and source document IDs) are attached for direct import into the knowledge graph system. Furthermore, to ensure data consistency, all entities are normalized according to a unified coding system; for example, different expressions such as "220kV transformer" and "20kV main transformer" are mapped to the same standard entity identifier. This process can also integrate manual verification interfaces or active learning mechanisms to continuously optimize dictionary and model performance.

[0034] For example, a method for semantic retrieval and reasoning of the target design task based on the knowledge graph includes: The task requirements of the target design task are analyzed to identify key entities. First, the input task requirement text is processed by natural language understanding to extract key entities with clear engineering meaning, such as "transformer". This entity serves as the starting anchor point for subsequent graph queries.

[0035] Using the key entity as the query node, semantic expansion and path traversal are performed in the knowledge graph to retrieve related entities and relationships. Semantic expansion refers to starting from the initial query node and performing multi-hop traversal along the established edges (i.e., relationships between entities) in the graph to explore other directly or indirectly related entities and relationship paths. The path traversal process supports multiple strategies, including depth-first, breadth-first, or weight-based heuristic search, ensuring that it can cover a wide range of relevant information while prioritizing the return of highly relevant results.

[0036] Based on the search results and preset inference rules, the system pushes multi-source data and associated participating units related to the target design task. The inference rules are constructed based on expert experience and historical data analysis, and can be expressed as logical expressions such as "If A is associated with B and B has solved a type C problem, then B is recommended to participate in the current type C task." Through the intervention of the rule engine, the system can not only push multi-source data directly related to the task (such as BIM models and material testing reports under similar working conditions), but also intelligently recommend participating units with corresponding technical capabilities or historical experience, such as specific design institutes, construction units, or third-party consulting agencies.

[0037] For example, the method for generating standardized collaborative workflows includes: Based on the associated participating units in the push notification, the entity responsible for executing the process is determined; Based on the relevant multi-source data from the push notification, the input data and output requirements of each execution entity are clearly defined; Based on the input data and output requirements, a standardized workflow containing task sequences, execution standards, and time nodes is generated through a preset power project collaborative work template.

[0038] When a new design task arises in a power engineering project, the system can automatically construct a well-structured, clearly defined, and standardized collaborative workflow based on the participating units and relevant data inferred from the prior knowledge graph. Because the workflow generation process is no longer heavily reliant on human experience, it significantly shortens the workflow development cycle, which can take days or even weeks in the traditional model. Furthermore, all similar tasks use a consistent template framework, effectively solving the problem of inconsistent workflow standards between different projects and improving execution consistency and compliance. In addition, by clearly defining input and output interfaces, it reduces communication costs caused by information asymmetry between units and improves cross-organizational collaboration efficiency.

[0039] For example, the method of returning the final processing result generated by the execution as new multi-source data and storing it in the collaborative design knowledge base includes: The final processing results undergo quality verification and version marking. Quality verification refers to automatically or manually reviewing the content of the processing results based on preset rules for data integrity, logical consistency, and business compliance to eliminate erroneous, contradictory, or non-compliant information. Version marking assigns a unique version number to each processing result, recording its generation time, number of modifications, and inheritance or replacement relationships with other versions, facilitating the tracing of historical evolution later.

[0040] The verified results are associated with corresponding project identifiers, task identifiers, and processing unit identifiers. The project identifier uniquely identifies the power engineering project to which it belongs, and is usually composed of a project code and name. The task identifier locates the specific design or decision-making task corresponding to the result, such as "main transformer foundation design optimization task". The processing unit identifier indicates the party responsible for generating the result, such as a design institute or construction unit. These identifiers together constitute a metadata tagging system, which is embedded in the attribute fields of the stored object to form structured index information.

[0041] The results after association and identification are stored in the collaborative design knowledge base according to a preset format, and the corresponding entities and relationships in the knowledge graph are updated. Since the output of each collaborative work is standardized, verified, identified, archived and fed back to the knowledge graph, the system has the ability to self-evolve, effectively solving the problems of experience loss and knowledge silos in traditional power project management, and building a dynamically evolving and continuously value-added intelligent decision support environment.

[0042] A second objective of this invention is to provide a task decision-making system for the entire lifecycle of power projects, comprising: Data acquisition module: used to acquire multi-source data from multiple participating units in the power project and to preprocess the multi-source data; Entity Relationship Extraction Module: Used to extract and structure key entities and relationships from preprocessed multi-source data; Knowledge storage management module: used to associate and store the processed structured data with the unstructured source data in the collaborative design knowledge base; Knowledge graph construction module: used to construct a knowledge graph for the power project domain based on the structured data in the collaborative design knowledge base; Retrieval and Reasoning Module: Used to obtain the target design task, perform semantic retrieval and reasoning on the target design task based on the knowledge graph, automatically match and push relevant multi-source data from the collaborative design knowledge base, and infer the associated participating units based on the knowledge graph; Process generation and execution module: Based on the pushed information, it generates a standardized collaborative workflow, executes the collaborative workflow, and returns the final processing result as new multi-source data to the collaborative design knowledge base to achieve closed-loop management of task decision-making.

[0043] In one embodiment of the present invention, a computer device is provided, comprising a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions from the computer storage medium to achieve corresponding method flows or corresponding functions. The processor described in this embodiment of the present invention can be used for the operation of task decision-making methods throughout the entire lifecycle of power projects.

[0044] This invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the task decision-making method for the entire lifecycle of power projects in the above embodiments.

[0045] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0046] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0047] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1The function specified in one or more boxes.

[0048] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0049] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A task decision-making method for the entire lifecycle of power projects, characterized in that, Includes the following steps: Acquire multi-source data from multiple participating units in the power project, and preprocess the multi-source data; Based on preprocessed multi-source data, key entities and relationships in the multi-source data are extracted and structured. The processed structured data is associated with and stored in the collaborative design knowledge base along with the unstructured source data. Based on the structured data in the collaborative design knowledge base, a knowledge graph for the power project domain is constructed. The target design task is obtained, and semantic retrieval and reasoning are performed on the target design task based on the knowledge graph. Relevant multi-source data is automatically matched and pushed from the collaborative design knowledge base, and related participating units are pushed out based on the knowledge graph. Based on the pushed information, a standardized collaborative workflow is generated, the collaborative workflow is executed, and the final processing result generated by the execution is returned as new multi-source data and stored in the collaborative design knowledge base to achieve closed-loop management of task decision-making.

2. The task decision-making method for the entire life cycle of power projects according to claim 1, characterized in that, The multi-source data includes: BIM model data, CAD drawings, and design calculation sheets from the design unit; project progress reports and change orders from the construction unit; on-site acceptance records and material testing reports from the construction unit; equipment operating parameters and fault reporting records from the operation unit; and geological survey data, meteorological monitoring data, and industry regulations and standards provided by third parties.

3. The task decision-making method for the entire life cycle of power projects according to claim 1, characterized in that, The method for preprocessing the multi-source data includes: S1. Identify and correct outliers, missing values, and format errors in the multi-source data; S2. Data from different participating units and in different formats are uniformly converted and mapped according to the preset power project data standards; S3. De-identify and encrypt fields involving trade secrets or personal privacy; S4. Assign unified project identifiers, stage identifiers, and professional identifiers to the processed data to support subsequent associated storage and traceability.

4. The task decision-making method for the entire life cycle of power projects according to claim 1, characterized in that, The method for extracting and structuring key entities and relationships in multi-source data includes: Based on a predefined entity dictionary and rule template for the power project domain, key entities are identified and extracted from preprocessed multi-source data. The key entities include at least project participants, equipment and facilities, design parameters, technical issues, specification clauses, and geographical locations. Based on the key entities, the contextual semantics are analyzed using a natural language processing model, and the relationships between the key entities are extracted according to the preset relationship types. The extracted key entities and relationships are organized and stored using a unified structured data model for constructing the knowledge graph.

5. The task decision-making method for the entire life cycle of power projects according to claim 1, characterized in that, The method for semantic retrieval and reasoning of the target design task based on the knowledge graph includes: Analyze the task requirements of the target design task and identify the key entities within them; Using the key entities as query nodes, semantic expansion and path traversal are performed in the knowledge graph to retrieve related entities and relationships; Based on the search results and preset reasoning rules, multi-source data and associated participating units related to the target design task are pushed out.

6. The task decision-making method for the entire life cycle of power projects according to claim 1, characterized in that, The method for generating standardized collaborative workflows includes: Based on the associated participating units in the push notification, the entity responsible for executing the process is determined; Based on the relevant multi-source data from the push notification, the input data and output requirements of each execution entity are clearly defined; Based on the input data and output requirements, a standardized workflow containing task sequences, execution standards, and time nodes is generated through a preset power project collaborative work template.

7. The task decision-making method for the entire life cycle of power projects according to claim 1, characterized in that, The method of returning the final processing result generated by the execution as new multi-source data and storing it in the collaborative design knowledge base includes: The final processing result is then subjected to quality verification and version marking. Associate the verified results with the corresponding project identifier, task identifier, and processing unit identifier; The results after association and identification are stored in the collaborative design knowledge base according to a preset format, and the corresponding entities and relationships in the knowledge graph are updated.

8. A task decision-making system for the entire lifecycle of power projects, characterized in that, include: Data acquisition module: used to acquire multi-source data from multiple participating units in the power project and to preprocess the multi-source data; Entity Relationship Extraction Module: Used to extract and structure key entities and relationships from preprocessed multi-source data; Knowledge storage management module: used to associate and store the processed structured data with the unstructured source data in the collaborative design knowledge base; Knowledge graph construction module: used to construct a knowledge graph for the power project domain based on the structured data in the collaborative design knowledge base; Retrieval and Reasoning Module: Used to obtain the target design task, perform semantic retrieval and reasoning on the target design task based on the knowledge graph, automatically match and push relevant multi-source data from the collaborative design knowledge base, and infer the associated participating units based on the knowledge graph; Process generation and execution module: Based on the pushed information, it generates a standardized collaborative workflow, executes the collaborative workflow, and returns the final processing result as new multi-source data to the collaborative design knowledge base to achieve closed-loop management of task decision-making.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1-7.

Images