37 results about "Feasibility study" patented technology

The invention discloses an automatic feasibility research report generation method fusing a knowledge graph and a large model, and relates to the technical field of leather inlaying, and the method comprises the following steps: extracting and cleaning information from multi-source heterogeneous data, and carrying out standardization processing on terminologies; constructing a knowledge graph, and converting the knowledge into embedded vectors which can be processed by a computer; according to user information, related sub-graph information is accurately retrieved from the knowledge graph, and cue words containing professional knowledge are dynamically combined; the large model generates a first draft according to cue words, a system automatically checks, and when conflicts are found, the model is required to be regenerated; and integrating the content which is verified to be correct with related standard terms, automatically adding a data reference source, and generating a document which is standard in format and clear in risk point. According to the method, real-time and automatic professional knowledge conformity checking and self-correction can be carried out on technical parameters and logic assertions output by the model in the generation process.

The invention discloses a method and system for generating an engineering design specification based on a large language model, and the method comprises the steps: converting a plurality of formats of engineering documents into structural data through a non-structural document analysis module, and carrying out the multi-modal storage through a vector database and a relational database; a document recall module is combined with an expert predefined generation strategy and user input information to intelligently retrieve related materials from a vector database; and finally, calling a large language model through a document generation module to rewrite, expand or independently generate recalled contents, and outputting a highly customizable design specification which conforms to engineering specifications. According to the method, the efficiency, accuracy and specialty of engineering design document generation are remarkably improved, multi-section concurrent generation and manual fine adjustment are supported, and the method is suitable for multiple engineering stages such as project proposal, feasibility research report and construction drawing design.

The invention discloses an intelligent compilation method for a feasibility research report fusing a big data model and artificial intelligence, relates to the technical field of information, and solves the technical problem that it is difficult to obtain quantized values from multiple aspects of market scale, project income and technology to analyze project feasibility. Comprising the following steps: collecting and preprocessing multi-source data; an ARIMA model is constructed to output a market scale prediction value, and partition assignment is carried out; processing corresponding structured data through XGBoost, analyzing time series data through Transform, predicting ROI and CBR through a full connection layer after feature fusion, and weighting to generate a comprehensive income evaluation index prediction value; calculating a technical equipment performance evaluation index and a technical improvement evaluation index; constructing a linear regression model, and outputting a comprehensive technology evaluation index prediction value; and calculating a score according to the market scale partition value, the comprehensive income evaluation index prediction value and the comprehensive technical evaluation index prediction value, comparing the score with a threshold value, and automatically generating an analysis report.

The invention provides a method for generating a highway engineering feasibility research report based on local large model training, which is based on a locally deployed large model, integrates multi-source data, and realizes mapping and verification from a fuzzy policy to a structured field through regular extraction of a standard field and construction of a highway engineering knowledge graph. The method adopts TensorRT to accelerate reasoning, injects a specification term table, optimizes term consistency in combination with comparative learning, and generates a specification text through LoRA fine tuning and a reward function. After route parameters are input, geometric features are calculated, a disaster database is associated to recommend a detour scheme, and chapter content is generated. And outputting a formal report based on the template, and ensuring data consistency through cross validation. RPA is adopted to capture standard updating, Kafka and Fiss vector libraries are combined to achieve compliance verification, knowledge graph incremental updating and conflict correction are triggered, and a full-process automatic and intelligent feasibility research report generation system is formed.

The invention provides a pre-auditing method and a pre-auditing system for power grid infrastructure main network project feasibility research initial setting. The method comprises the following steps: obtaining feasibility research review related data and initial setting review related data in various formats; carrying out character extraction, picture extraction and table extraction on the research and review related data and the initial review related data through a natural language processing component and an engineering drawing analysis component to obtain pre-input content; creating a rule engine based on an electric power engineering pre-review specification file, constructing a deep learning model, and training the deep learning model by taking the pre-input content as input and the review result as output; and reviewing the feasibility review related data and the initial review related data through the trained deep learning model, and outputting a review result as a visual report by applying a template. According to the invention, the files of the power grid project can be preliminarily reviewed automatically, and the efficiency is improved.

A system and method for labelling normal and abnormal regions in data related to a paper machine for web break prediction and labelling individual parameters for root cause analysis, using machine learning models, includes using the machine learning models in real-time to predict breaks in the paper web, analyzing root cause for the breaks in the paper web, and estimating a time to break. An auto-data-labeling framework helps in adaptive learning for autonomous model improvement of the deployed model, transfer learning, shortlisting parameters and automating feasibility study.

The invention discloses a capital construction feasibility investigation automation standard compliance verification method and system, relates to the technical field of data verification, and solves the problems that feasibility investigation in the prior art mainly depends on manual examination and is low in efficiency, high in subjectivity and easy to omit. According to the method, automatic checking of capital construction research and review automation standard compliance verification is realized through an intelligent algorithm, manual intervention is reduced, and the checking efficiency is improved; moreover, the advanced intelligent technology is utilized, so that the accuracy and the consistency of a verification result are improved; in addition, the standard library can be dynamically adjusted according to the updating of the capital construction feasibility research standard, so that the automatic standard compliance verification requirements of capital construction feasibility research examination in different regions and in different scales are met; moreover, the automatic standard compliance verification system for capital construction research and review can be upgraded and optimized according to actual requirements, so that the maintenance cost is reduced.

The application provides a power distribution network feasibility report automatic generation method based on an LDA probability model, including: obtaining power grid equipment account information and electrical topology connection relationship, generating an account document containing equipment name, type, position, connection relationship information; taking the obtained account attribute and electrical topology relationship as a benchmark grid graph structure, and marking out standby line and standby equipment data, generating a marking document containing the benchmark grid structure and marking information; training an LDA model, setting the number of topics, performing iterative training, extracting the topic distribution of each document and the vocabulary distribution of each topic; based on the redundancy information, a feasibility report generation model is constructed, the feasibility report generation model is used for analyzing potential topics and modes in the redundancy information, and a power distribution network redundancy feasibility report is generated.

The invention relates to the technical field of engineering quantity digital statistics, in particular to an automatic engineering quantity calculation method and system based on a generated structure model, and the method comprises the steps: constructing a mapping table containing statistical items, data sources and calculation rules; filtering the structure model according to the type of the beam body, and extracting family examples and geometric parameters of the beam body and matched components; performing direct acquisition, formula calculation or correlation statistical operation on a hierarchical execution model; and generating a standardized engineering scale and embedding a design drawing. The system comprises a rule configuration module, a data extraction module, an engineering quantity calculation module, a scale generation module and a result output module. According to the method, the engineering quantities of concrete, reinforcing steel bars, drainage components and the like can be automatically and accurately counted, research, initial setting and construction drawing stage precision adjustment are supported, dynamic linkage updating can be achieved when model parameters are changed, manual errors are avoided, the technical and economic comparison and selection and cost control efficiency is improved, and the statistical requirements of professional components of water conservancy projects are met.

The invention relates to the technical field of power grid infrastructure projects. The invention discloses a structured design method and system for a feasibility research report of a power grid infrastructure project. The method comprises the steps of obtaining file data specified by related management of power grid infrastructure in a historical file library, and obtaining a structured text data set; performing structured information extraction on the text data set to obtain a structural framework set of the text; key review element extraction of the feasibility research content review rule is carried out on the text data set, and a key review element set is obtained; establishing logic association for each key review element, each node and each text in the text data set to obtain a mapping relation M of the key review element ID, the node ID and the text ID; according to the mapping relation M, a feasibility research report structure chart is formed, and a power grid infrastructure project feasibility research report template is created. The produced standardized template provides a solid and uniform data basis for treatment, integration and deep analysis of power grid data, thereby directly supporting scientificity and accuracy of investment decision.

This utility model discloses a shared structure for ventilation and safety tunnels in a phased development hydropower station in the field of water conservancy and hydropower technology. It includes two underground powerhouse cavern groups: Group 1 and Group 2. Access tunnels 1 and 2, respectively, are located at opposite ends of Group 1 and Group 2, connecting their interiors to the surface. At the end of Group 1 closest to Group 2, a branch tunnel 1 for ventilation and safety tunnels and a main tunnel for air intake and safety tunnels are located, connecting their interiors. A branch tunnel 2 for ventilation and safety tunnels, connecting to the interior of Group 2, branches off from the main tunnel. An underground powerhouse exploration tunnel also branches off from the main tunnel. This utility model, by branching off the underground powerhouse exploration tunnel from the main tunnel, can significantly shorten the length of the exploration tunnel, effectively reducing project investment and the design period during the feasibility study and survey phases.

The present invention discloses a method, system and device for intelligent parsing and information extraction of a feasibility study report, which relates to the fields of natural language processing and machine learning technology. The method is to first identify each chapter title in the report text by using a regular expression or a syntactic analysis method based on natural language processing technology after reading the feasibility study report document to obtain the report text, and determine the title category of each chapter title according to the title hierarchy structure. Then, for any chapter title whose title category belongs to the key objects of report review, the corresponding chapter content is extracted from the report text, and key business information is extracted from the chapter content by combining the Word2Vec model, named entity recognition and semantic matching technology. Finally, each chapter title and the corresponding title category / and key business information are summarized and output for display. This method has the advantages of high efficiency, high accuracy, versatility, high intelligence and scalability of information extraction.

The application provides a method for generating a feasibility study report of highway engineering based on local large model training, based on the large model deployed locally, integrating multi-source data, extracting standard fields through regularization and constructing a highway engineering knowledge graph, realizing the mapping and verification of fuzzy policies to structured fields. Adopting TensorRT to accelerate inference, injecting a standard terminology table, combining contrast learning to optimize terminology consistency, and generating standard text through LoRA fine-tuning and reward function. After inputting the route parameters, calculate the geometric characteristics, recommend the avoidance scheme by associating the disaster database, and generate chapter content. Based on the template, output the formal report, and ensure data consistency through cross-validation. Adopting RPA to grab the standard updates, combining Kafka and Faiss vector library to realize compliance verification, triggering incremental update and conflict correction of the knowledge graph, forming a full-process automated and intelligent feasibility study report generation system.

The embodiment of the invention provides a power grid project comprehensive risk knowledge base construction method and device, equipment and a medium, and the method comprises the steps: obtaining project data of each power grid project, the project data comprising a feasibility research report, a management file and a risk management case; according to the feasibility research report, the management file and the risk management case, determining a target risk feature of each type of power grid project; according to a causal relationship between a risk source class and a risk class in the target risk characteristics of each class of power grid projects, constructing a risk ontology model of each class of power grid projects; and determining a power grid project comprehensive risk knowledge base according to the risk ontology models of different types of power grid projects. Alignment and fusion of entities in different special risk ontology models are realized, a unified comprehensive risk knowledge base is formed, information barriers among special items are broken, and cross-special associated risk analysis and macroscopic decision are supported.

The invention provides a wind and light same-field power station layout method considering the influence of a photovoltaic array on a wind power plant, and belongs to the technical field of renewable energy source development, and the method comprises the steps: constructing a photovoltaic array entity model in a target wind and light same-field power station, carrying out the CFD simulation, and obtaining the flow field distribution of the photovoltaic array; obtaining the equivalent roughness distribution of the photovoltaic array by using an equivalent roughness calculation model considering the influence of the photovoltaic array, calculating the generating capacity of the wind turbine generator set at the preset candidate position based on the equivalent roughness distribution of the photovoltaic array and the common sea surface roughness distribution without considering the influence of the photovoltaic array, and obtaining the generating capacity loss distribution of the wind turbine generator set; and obtaining the site selection of the photovoltaic array and the wind turbine generator in the wind-solar same-field power station by combining the power generation loss distribution of the wind turbine generator. According to the method, the influence of the photovoltaic array on the wind field is quantitatively evaluated through the equivalent roughness, the precision of flow field coupling analysis of the wind-light same field is improved, and a scientific basis is provided for feasibility research, layout optimization and income evaluation of the wind-light same field.

The invention belongs to the technical field of power equipment monitoring, and particularly relates to an artificial intelligence-based power engineering supervision and monitoring method and system, and the method comprises the steps: obtaining an authorized technical improvement and overhaul project list from a power grid resource business platform in response to successful login, building the correlation between a supervision and monitoring device and a target project, and carrying out the supervision and monitoring of the target project; downloading feasibility research report structured data corresponding to the project, an associated power equipment asset code and power industry mandatory regulation text data of a specialty to which the project belongs; according to the invention, through double authentication of face living body detection and passwords in the step S1, unique binding of'human-machine-account 'is ensured, and false use of the identity is completely eradicated; and S3, Beidou differential positioning and anti-metal electronic tag scanning are creatively fused, the positioning precision is improved to a meter level / sub-meter level in a 500kV strong electromagnetic interference environment, whether a supervisor accurately arrives at an equipment operation point or not is directly checked, the recognition rate of virtual post behaviors such as card punching and regional wandering is improved, and supervision is guaranteed to perform in place from the source.

The invention discloses a multi-dimensional coupling abandoned mine large-scale physical energy storage potential grading evaluation method, belongs to the field of mine resource utilization, and aims to solve the problem that a multi-dimensional decision-making system for resources, society, engineering, economic environment and the like exists when abandoned mine resources are used for large-scale physical energy storage development in China at present. The invention provides a scientific, accurate and efficient multi-dimensional coupled abandoned mine large-scale physical energy storage potential grading evaluation method for solving the problems of insufficient adaptability of different energy storage technical routes and abandoned mine resource conditions and the like. The potential of the abandoned mine for large-scale physical energy storage is evaluated through the processes of preliminary screening, detailed technical evaluation, economic evaluation, risk quantification, comprehensive decision making and the like, the method is used for the feasibility research stage of related projects, then engineering decision making and project investment are directly guided, and the method has remarkable positive effects and industrial practicability.

The application discloses a kind of causal screening and joint optimization's hydropower engineering investment prediction method and system, belong to hydropower engineering cost prediction technical field.For the feature causal structure is not clear in hydropower engineering investment prediction, dimension reduction and modeling parameter split optimization leads to low prediction accuracy under small sample high-dimensional data, poor generalization ability, the application adopts double machine learning algorithm to carry out causal inference screening key influence factor, constructs the joint prediction model of partial least square regression and support vector regression, through improving bayesian optimization to jointly optimize dimension reduction dimension and support vector regression hyperparameter, and feature standardizer, partial least square dimension reducer and support vector regression predictor are serialized and solidified into independently loadable model package.The application significantly improves prediction accuracy and robustness, realizes the engineering closed loop from parameter input to investment prediction, and is suitable for rapid investment estimation in the feasibility study stage of hydropower engineering.

The invention provides a project decision and effect prediction method and device based on expert knowledge extraction and a medium, and belongs to the technical field of power grid enterprise achievement transformation management. The method comprises the following steps: receiving a feasibility research report text and expert review data, and extracting a core text through a keyword matching rule; carrying out word segmentation and segmentation on the extracted content by using a built-in word segmentation device of the pre-training language model, obtaining vector representation of each segment, and distributing a weight to each segment based on an attention mechanism; unifying the dimension of the expert review score in the expert review data; constructing a deep learning model based on pre-training BERT, and adopting a staged progressive training strategy; and collecting a feasibility research report text to be decided, inputting the trained deep learning model, and outputting a project approval decision. According to the method, through intelligent processing of the feasibility research report text and the expert review data of the incubation project, the structured review knowledge is extracted, the deep learning model is constructed, and the project optimization efficiency and consistency are remarkably improved.

This application discloses a method, apparatus, electronic device, and medium for calculating the heating capacity of geothermal fields based on pressure field factors. The method may include: determining the expression of a well function based on a single-well extraction model; calculating the well-to-well spacing in the well-to-well model, which includes pumping wells and reinjection wells, based on the expression of the well function; calculating the heat extraction capacity of a single well; calculating the number of pumping wells based on the well-to-well spacing; and calculating the heating capacity based on the heat extraction capacity of a single well and the number of pumping wells. This invention starts from the changes in the pressure field of a geothermal field to determine a reasonable spacing between extraction and reinjection wells to ensure the relative stability of the pressure field and avoid a significant drop in the liquid level of pumping wells. Based on the well spacing, a geothermal field development well network is deployed, and the scale of geothermal field development and utilization and the geothermal heating capacity can be further calculated, providing a scientific basis for the sustainable development and utilization of geothermal fields and the preparation of feasibility studies for geothermal heating projects.

The invention discloses a hydraulic machinery feasibility research report intelligent review method and system. The method comprises the following steps: constructing a data layer, a model layer and an application layer; a multi-source data acquisition module of a data layer is adopted to access three types of heterogeneous data sources and carry out intelligent adaptation, cross-modal cleaning preprocessing is carried out on acquired data, then the data are input into a hierarchical and classified storage module, and a domain knowledge base is constructed; constructing a large language model, optimizing large language model parameters based on hydraulic machinery field annotation data, inputting a to-be-examined document into the large language model to obtain a core field, and inputting the core field into a compliance comparison verification module for verification; constructing an intelligent risk assessment system, generating a risk distribution thermodynamic diagram to display the risk level of each index, constructing a strategy matching unit association library based on a domain knowledge base, outputting a coping strategy, and performing structured display on an examination result. According to the method, multi-modal intelligent analysis, compliance accurate verification, risk quantitative evaluation and man-machine collaborative optimization of the hydraulic machinery feasibility research report are realized.

The invention discloses a power grid infrastructure project group investment management whole process risk monitoring method comprising the following steps: carrying out project group division on a power grid infrastructure project based on an electrical connection principle to obtain an extra-high voltage project group and a matched project group thereof, and an electrified railway matched electric power project group for partially supplying power to the same railway; a project group investment management whole-process monitoring index system is established according to the whole life cycle of a power grid infrastructure project, wherein the monitoring index system comprises monitoring indexes of five stages, namely a feasibility research stage, a planning stage, a project early stage, a construction stage and a settlement stage; calculating an actual value of each monitoring index, comparing a calculation result with an early warning threshold value, and when the monitoring index cannot be calculated, displaying that the monitoring index is null; when the monitoring index calculation result exceeds an early warning threshold value, a prompt or an alarm is displayed; and when the monitoring index calculation result does not exceed the early warning threshold value, the display is normal. According to the invention, the early warning mechanism of the monitoring indexes is optimized, and the timeliness and accuracy of risk early warning are improved.

This invention relates to a method for energy efficiency evaluation of long-span flexible high-support and bifacial photovoltaic (PV) module systems. The method includes: acquiring the azimuth and elevation angles of a target; determining the tracking angle of the bifacial PV module system based on the target's azimuth and elevation angles; calculating the front and back irradiance of the bifacial PV module system at different tracking angles combined with different north-south spacing and support heights; obtaining the total irradiance of multiple bifacial PV module systems; and selecting the tracking angle, north-south spacing, and support height corresponding to the maximum total irradiance as the optimal target tracking result; acquiring the ambient temperature, diffuse reflection, dust levels, and dynamic shadows formed by the north-south spacing of the bifacial PV module system; and performing energy efficiency evaluation based on these factors to obtain the energy efficiency evaluation result of the bifacial PV module system. This invention can improve the accuracy of economic and technical feasibility studies.

The invention provides an engineering project feasibility research analysis-oriented geographic information knowledge graph construction method, which is used for deeply mining complex relationships among geographic elements by fusing multi-source geographic information data, and carrying out structured organization and efficient storage in a knowledge graph form. The method comprises the steps of geographic information data collection, data preprocessing and enhancement, knowledge graph construction, geographic element extraction model construction, entity knowledge matching and fusion and the like. According to the method, comprehensive, accurate and dynamically updated geographic information support can be provided for engineering project feasibility research and analysis, and the efficiency and scientificity of engineering research and analysis are remarkably improved.

This invention discloses a hierarchical review method for hydraulic machinery feasibility study reports based on a large language model. The method involves collecting and parsing the original hydraulic machinery feasibility study report to generate a logical structure tree and structured text. Based on the logical structure tree, hierarchical gating and strategy scheduling are performed to generate gating scheduling data. According to the review strategy parameters in the gating scheduling data, the structured text is subjected to three-constraint parallel block partitioning to obtain a set of sub-documents. Using the gating scheduling data, an auditable adversarial compliance review is performed on each sub-document in the sub-document set to form a preliminary review conclusion set. The preliminary review conclusion set is aggregated, and cross-sub-document consistency adjudication and result summarization are performed to generate a final review conclusion. This invention completely and accurately identifies compliance issues in long-form hydraulic machinery feasibility study reports.

The application provides a project whole-process safety data monitoring method and system, which comprises the following steps: establishing a safety monitoring and evaluation system in a project feasibility study stage, a project acceptance stage and a project operation stage based on project whole-process planning data and input process data; determining a data collection and monitoring strategy in the project whole process based on the safety monitoring and evaluation system; obtaining monitoring data according to the data collection and monitoring strategy; performing safety evaluation on the monitoring data based on the safety monitoring and evaluation system to obtain a safety evaluation result; and setting a hierarchical early warning reminder in the project whole process based on the safety evaluation result, so as to realize the monitoring, analysis and early warning of data safety in the project whole process, realize the construction of a healthy enterprise, ensure the safety of employees and improve the production efficiency.

The invention discloses a project cost data visualization analysis and decision support method and system, and relates to the technical field of project cost, and the method comprises the steps: carrying out the element extraction of a preliminary design drawing and a feasibility research report based on preset data elements, obtaining target data, and generating a preliminary cost estimation table based on the target data; constructing a basic model and associating the initial cost estimation table with components of the basic model to obtain an initial model; updating the initial cost estimation table and the initial model based on a dynamic recheck mechanism to obtain a current cost estimation table and a current model; performing cost deviation evaluation on the current cost estimation table based on a dynamic scoring mechanism to obtain a cost deviation evaluation result corresponding to the current cost estimation table; and generating a visual billboard based on the current model and the cost deviation evaluation result. According to the invention, coherent analysis of full-cycle data can be realized, so that the cost estimation deviation is reduced, and the accuracy of cost management and control is improved.

The invention discloses a power grid digital project cost measuring and calculating method and system based on multi-dimensional feature aggregation, and the method comprises the following steps: extracting and quantifying multi-dimensional features from a feasibility research report of a power grid digital project based on a natural language processing technology, and constructing a feature pool; a dual-channel measurement and calculation module is adopted to carry out preliminary measurement and calculation on project cost, and research and development type cost and non-research and development type cost are calculated respectively; based on historical project settlement data, training by adopting a gradient boosting decision tree regression algorithm to obtain a dynamic weight vector, and then carrying out weighted fusion on research and development fees and non-research and development fees to obtain project measurement and calculation fees; and carrying out multiple times of random sampling on the feature values in the feature pool by using a Monte Carlo method, generating statistical distribution of project measurement cost, determining a confidence interval of the cost according to the statistical distribution, and providing a scientific risk reference for budget review. According to the invention, the cost calculation precision can be improved, and the quantitative evaluation of the budget risk can be realized.

The invention discloses a risk assessment method for intrinsic safety design, which is applied to electric power engineering and comprises the following steps: identifying risk categories in a full life cycle; the full life cycle comprises a feasibility research stage, a design stage, a construction stage and an operation stage; according to the identified risk categories, identifying hazard factors of each risk category; forming a risk check list according to the identified hazard factors of each risk category; the risk check list comprises risk check items corresponding to the risk categories; according to the risk check list, obtaining a risk category with a risk and a risk score of the risk category with the risk, and determining a risk level of the risk category with the risk according to the risk score; and performing risk assessment on the risk category with the risk according to the risk level. By adopting the technical scheme, the risk assessment is performed on the intrinsic safety design of the electric power engineering, so that the risk is pre-controlled according to the risk assessment result, and the intrinsic safety is realized.

The invention discloses an offshore wind resource refined evaluation method and device based on multi-source data fusion. The method comprises the following steps: firstly, constructing high-resolution longitude and latitude information according to wind resource refined evaluation requirements; collecting multi-source wind speed data, wherein the multi-source data comprises a numerical weather forecast result and satellite remote sensing data; under the same timestamp, taking latitude and longitude information and high-resolution latitude and longitude information of the multi-source data as input, taking wind speed data in the multi-source data as output, and training a common Kriging interpolation model; after training is completed, high-resolution wind speed data corresponding to the high-resolution latitude and longitude information can be obtained. Compared with a traditional method, the method has the advantages that advantage complementation of multi-source data is achieved, limitation of a single data source in the aspects of space coverage, time consistency and measurement precision is overcome, high adaptability and generalization performance are achieved, and the method is particularly suitable for deep and far sea areas where data are difficult to obtain; and wind power site selection, resource evaluation and feasibility research are effectively supported.