71 results about "Cost prediction" patented technology

The invention discloses an AI and BIM-based project cost control method and system, and the method comprises the steps: obtaining the three-dimensional model data of a target building, analyzing the file structure of the three-dimensional model data, recognizing the type, size parameters and material attributes of a component, building a mapping relation between a component coding system and an attribute tag if the three-dimensional model data passes the integrity inspection, and carrying out the construction cost control of the target building. Generating a standardized component data set; constructing a material price fluctuation prediction model according to the historical price record, intercepting time series data by adopting a sliding window mechanism, and if the price fluctuation amplitude in the material price fluctuation prediction model exceeds a preset threshold, triggering an early warning identifier, and generating cost prediction data with a risk level; and carrying out association mapping on the standardized component data set and a quota library by adopting a coding matching mechanism, and if component attributes are successfully matched with quota entries, converting and generating engineering quantity data based on geometric parameters, and calculating the cost of a single project. The cost prediction accuracy is improved.

The invention discloses a medical health cost prediction system and method based on multi-source data fusion, and relates to the technical field of medical data analysis, the system firstly fuses a plurality of heterogeneous medical information sources to generate structured data; then, multidimensional features related to the cost are extracted to construct a feature representation vector; and the cost prediction modeling module constructs a cost prediction model through graph structure modeling and semantic embedding, carries out joint optimization by combining a graph attention mechanism and semantic similarity, and outputs a prediction result by fusing a time sequence and static characteristics. A joint optimization algorithm of graph semantic comparison loss and prediction deviation loss is introduced into model training, and positive and negative sample pairs are constructed through a cost label distance. And the feedback optimization module triggers model updating when the prediction deviation exceeds a threshold value, and dynamically adjusts a model structure and parameters through a deviation index and a sample confidence factor. And the prediction interpretation module analyzes influence factors based on intermediate layer features or gradient propagation, outputs an interpretation report, and improves the transparency and credibility of the model.

The invention relates to the technical field of industrial equipment predictive maintenance and asset management, in particular to a machine vision equipment operation and maintenance cost analysis intelligent management method, which comprises the following steps of: acquiring equipment operation state, external environment and historical operation and maintenance work order data through a sensor group and an equipment log interface, and fusing and removing redundancy to form a multi-source data stream; static and dynamic features are extracted by using a pre-trained health state evaluation model and fused by means of an attention mechanism, and a real-time health state index in a 0-1 interval is output; constructing a dynamic cost prediction model, taking health related parameters, spare parts, manpower and depreciation cost as input, and predicting expected operation and maintenance cost of a specific time window in the future; establishing an optimization decision model by taking minimization of the total operation and maintenance cost and maximization of the equipment availability rate as double targets, and generating an optimal maintenance, spare part purchasing and scheduling scheme; and executing the scheme and acquiring actual data, comparing the actual data with a predicted value for feedback, and iteratively optimizing the core model. The operation and maintenance management accuracy and economy are improved, and the method is suitable for intelligent operation and maintenance of the machine vision equipment.

The invention provides a project cost intelligent management and control method and system based on dynamic multi-dimensional modeling in the technical field of project management and intelligent decision technology crossing. The method comprises the following steps: S1, creating a project cost prediction model; s2, acquiring a large amount of historical project data to construct a data set; s3, dividing the data set into a training set, a verification set and a test set, training the project cost prediction model through the training set, and verifying and testing the trained project cost prediction model through the verification set and the test set; s4, acquiring real-time project data, preprocessing the real-time project data through a streaming computing engine, and inputting the preprocessed real-time project data into the project cost prediction model to obtain a project cost prediction report; and S5, executing project cost management and control based on the project cost prediction report. The method has the advantages that the reliability, timeliness, accuracy and flexibility of project cost management and control are greatly improved.

The invention discloses a project cost data visualization monitoring method and system, and the method comprises the steps: building a causal conduction path of a project digital twinborn dynamic simulation risk event, quantifying the increment influence on a cost chain, and combining the prediction capability of a machine learning model for the overall cost trend, thereby achieving the visual monitoring of the project cost data. And carrying out fusion calculation on the local cost increment caused by the sudden risk and the global predicted value to generate a final total completion cost predicted value which reflects the macroscopic trend and contains the impact of the sudden event, and finally dynamically rendering a fusion prediction result in a three-dimensional model space through a unified visualization engine. Thus, the defect that static BIM association lacks risk conduction analysis is overcome, the problem that a traditional prediction model and construction logic are unhooked is solved, a decision view with the overall trend control and emergency traceability is provided for engineering managers, engineering cost management is fundamentally promoted to be converted from post-event accounting to pre-control, and the engineering cost management efficiency is improved. And the cost anti-risk capability of the complex engineering project is obviously improved.

The invention provides an iron-making production ore blending process method based on multi-target intelligent optimization and dynamic feedback regulation. The method comprises the steps that ore components, price and production data are collected, a quality and cost prediction model is built, a multi-target optimization model is built with molten iron quality, cost, blast furnace smooth operation and environmental protection as targets, and a Pareto optimal ore blending scheme is solved through an evolutionary algorithm. And real-time data is monitored on line, model predictive control is triggered to automatically adjust ore blending when setting is deviated, a sintering-pelletizing-blast furnace collaborative simulation model is built to optimize cross-process parameters, solid waste classified recovery and resource utilization are synchronously implemented, and intelligent low-carbon ironmaking is achieved. The method can improve the quality of molten iron, reduce the production cost, improve the operation efficiency of a blast furnace, reduce pollutant discharge, realize resource utilization of solid wastes, and improve the comprehensive benefits and environmental protection level of ironmaking production.

The invention discloses a project cost prediction method fusing MDS-LOF and GBRT. The method comprises the steps of S1, selection and primary processing of project cost data; s2, performing project feature analysis and reserving core data; s3, performing dimension reduction processing by using a multi-dimensional scaling analysis (MDS) method; s4, using a local outlier factor (LOF) algorithm to identify abnormal values and removing the abnormal values; s5, training is carried out by using the GBRT prediction model and the processed data, and a trained model is obtained; and S6, outputting and verifying the trained prediction model. According to the invention, by constructing the adaptive prediction model, the influence caused by sudden policy regulation and control is weakened, so that the project cost prediction result is more in line with the market law of the building construction cost, and scientific basis and reference value are provided for project early-stage decision making and cost prediction of investment subjects such as enterprises and governments in a complex policy environment period.

The invention relates to the technical field of project cost, and discloses a method, a system, equipment and a medium for precisely checking a cost range based on geographic region characteristics, and the method comprises the steps: collecting project engineering data, and carrying out the data preprocessing; performing feature extraction based on the project engineering data to obtain project geographic features and engineering cost features, and performing feature analysis; constructing a project construction cost model, and calculating to obtain a project construction cost prediction range; and comparing the construction cost with a preset construction cost range to check the construction cost, judging whether the construction cost exceeds the preset construction cost range or not, and adjusting and optimizing the project construction cost if the construction cost exceeds the preset construction cost range. According to the method, the cost range of various engineering projects in different geographic areas can be predicted, the prediction precision is improved, through comparison with actual cost data, the prediction accuracy is evaluated by adopting a statistical method, the high accuracy of the final cost range is ensured, and a visual and comprehensive decision basis can be provided for a decision maker according to a cost check result.

The invention belongs to the technical field of constructional engineering, and particularly relates to a self-adaptive constructional engineering cost control method and system. A load sensor installed on a tower crane is used for monitoring the weight of a hoisted material, the number of hoisting times is combined, the real-time using amount of the material is calculated through a formula, and a big data analysis technology and a machine learning algorithm are used for constructing a cost prediction model. Factors such as manual efficiency change coefficients at different construction stages, shutdown time length caused by abnormal weather and additional cost coefficients caused by the shutdown time length are considered, and the cost change trend can be accurately reflected; the problems that a traditional construction engineering cost control method cannot adapt to various uncertain factors in engineering, so that cost prediction is not accurate, and coping strategies are lacked are solved, cost hyper-branched and resource waste are prevented, and the problems of accurate control and efficient management of cost are solved.

The invention relates to a financial cost prediction method and device based on machine learning, equipment and a medium. The method comprises the steps of performing dimension reduction processing according to enterprise financial data to obtain a dimension-reduced data set; performing invisible feature analysis to generate an invisible feature set containing periodic fluctuation features and project association features; generating an initial prediction model based on the set training; analyzing the importance of each invisible feature and screening reliable feature subsets; performing cross-scene verification on the initial model through the subset to generate a stability index, and further optimizing the model; and inputting real-time financial data into the optimized model, and outputting a cost prediction result. By adopting the method, the problem of insufficient prediction accuracy and stability caused by ineffective processing of high-dimensional data, excavation of invisible features and verification of model stability in the existing method can be solved, and the accuracy and reliability of financial cost prediction are improved.

This invention provides a method for predicting staple food costs and related hardware, comprising: performing the following steps on any target staple food: acquiring cost data corresponding to multiple cost data items of the target staple food in different statistical periods; for any statistical period other than the baseline statistical period, determining at least one change characterization data corresponding to any cost data item; the change characterization data includes at least one of year-on-year data and month-on-month data; for any statistical period other than the baseline statistical period, determining a comprehensive evaluation index corresponding to the statistical period based on each change characterization data of each cost data item and the influence weight corresponding to each change characterization data; and determining the predicted cost of the target staple food in future statistical periods based on the comprehensive evaluation index corresponding to each statistical period and the cost data corresponding to each cost data item in at least some statistical periods.

The invention relates to the technical field of oil and gas field production cost prediction methods, in particular to an oil and gas operation cost prediction method and device.The oil and gas operation cost prediction method comprises the steps that a block similar to a block to be predicted is searched in historical data, and the single well cost and the single well liquid amount of the similar block in the Nth year and the (N-1) th year are obtained; based on the single well cost of the Nth year and the N-1 year, the single well fixed cost and the ton liquid variable cost are calculated; obtaining the well opening number and the liquid production capacity in the to-be-predicted block; and calculating the operation cost of the to-be-predicted block based on the single well fixed cost, the well opening number, the ton liquid variable cost, the liquid production capacity and the oil production capacity. The single well fixed cost and the ton liquid variable cost of the to-be-predicted block are rapidly and accurately calculated, the problem that classification of the fixed cost and the variable cost of a related factor method is inaccurate is solved, the problem that an overall assignment method is influenced by human factors is solved, and the problem that classification of the fixed cost and the variable cost is difficult is solved; the purpose of preventing prediction from being influenced by human factors is achieved.

The embodiment of the invention provides a cost prediction method and device, and the method comprises the steps: inputting a target image carrying a target process into an image recognition model, obtaining target process data outputted by the image recognition model, and enabling the target process data to comprise a process color register number and a process size; determining a first prediction cost from cost storage data according to the target process data, and determining a first cost prediction curve according to the first prediction cost and a first piece number range; performing combined calculation on the target process data and production parameter data corresponding to the target process to obtain a second cost prediction curve, the production parameter data including the second piece number range; determining a target cost prediction curve according to the first cost prediction curve and the second cost prediction curve, and determining a target cost corresponding to a target number from the target cost prediction curve; and based on a unified standard prediction mode, a prediction result is stably and efficiently output.

The invention relates to a dynamic project cost intelligent prediction method, system and equipment, and the method comprises the steps: anchoring a prediction dimension through a cost motivation map through a closed-loop process of cost motivation quantification, multi-source data structuring, feature engineering and hybrid model dynamic prediction, and carrying out the directional mapping from multi-source data to a cost motivation dimension, performing corresponding feature processing according to feature types on the basis of feature classification defined by the cost motivation quantization atlas to form a structured feature set for model training; project data of different stages are input into a trained mixed cost prediction model, dynamic project cost prediction is achieved, and the mixed cost prediction model comprises an XGBoost model used for extracting static features and an LSTM model based on extracted historical time series data features. Compared with the prior art, the method has the advantages of realizing more accurate and more adaptive project full-stage dynamic cost prediction and the like.

The invention relates to the technical field of building construction management, and discloses a building outer wall construction cost prediction and control system based on big data analysis, and the system comprises a data collection module, an analysis engine, a decision support module and a visualization module. The core method comprises the following steps: calculating a construction behavior entropy based on high-frequency dynamic data collected from a construction site through an analysis engine so as to quantify the disorder degree of an operation process; a cost potential energy model is established in combination with the construction behavior entropy and the external environment constraint and is used for quantifying the risk of actual cost hyper-branched in the future; and constructing a conduction network based on a working decomposition structure (WBS) to predict an evolution path of the risk, and diagnosing a systematic source by identifying resonance between behavior entropies of different dimensions. According to the method, dynamic quantification, predictive identification and root diagnosis of cost risks can be realized, passive control is changed into active intervention, and the perspectiveness and the refinement level of project cost management are remarkably improved.

The invention provides a fabricated building cost prediction method based on an XGBoost algorithm. The fabricated building cost prediction method comprises the following steps: selecting a plurality of key feature indexes influencing the fabricated building cost by using a Pareto technology; collecting index data corresponding to each key feature index of the plurality of prefabricated construction projects, and preprocessing each index data; and for each fabricated building project, fitting the preprocessed index data of the fabricated building project by using an XGBoost algorithm to obtain the predicted building cost of the fabricated building project, and optimizing the parameters of the XGBoost algorithm based on the real building cost of the fabricated building project. A fabricated building cost prediction model is obtained; and obtaining index data corresponding to each key feature index of a to-be-predicted fabricated building project, and performing building cost prediction by using the fabricated building cost prediction model. According to the method, the precision and efficiency of prefabricated building cost prediction are improved.

The invention relates to the technical field of data analysis, and discloses a smelting cost prediction method and system based on data analysis, and the method comprises the following steps: collecting multi-source data of the same metal material and the metal smelted by the same production line in the smelting process, the multi-source data comprising material data, energy consumption data, production operation data and actual marginal cost increase rate; preprocessing the multi-source data, wherein the preprocessing comprises data cleaning, missing value filling, abnormal value detection and data normalization; static features and dynamic features related to the smelting cost are extracted based on the preprocessed data. According to the invention, by fusing the multi-source data and respectively extracting the static and dynamic characteristics by using the convolutional neural network and the recurrent neural network, the stable and changing cost influence factors in the smelting process can be comprehensively captured, so that the comprehensiveness and accuracy of cost prediction are remarkably improved; and the defect of insufficient consideration of time sequence dynamic factors in a traditional method is overcome.

This invention proposes a product cost prediction method, system, and electronic device using a multi-mode interpolation strategy, relating to the field of data processing technology. The method includes acquiring product cost data to be predicted; determining whether missing values ​​exist in the product cost data; if missing values ​​exist, judging the significance of the trend and seasonality of the cost data based on set rules, and dynamically interpolating for each case to obtain the interpolation result corresponding to the missing value; and inserting the interpolation result into the corresponding position in the cost data to be predicted, thereby achieving product cost prediction. This invention performs qualitative analysis of the trend and seasonality of the cost data to be predicted, classifies cases according to the significance of the trend and seasonality, and automatically assigns different interpolation models to form interpolated data. This ensures that the exponential smoothing algorithm remains usable even when the time series is interrupted, and guarantees prediction accuracy.

The present application relates to a kind of hierarchical cost intelligence accounting method, belong to cost intelligence accounting field.The method includes five main steps.Cost data is obtained, cost data is preprocessed, and cost data is divided into training set and test set;Weighted time series additive decomposition model is built, and cost data in training set is extracted by data after model, and trend item, seasonal item and residual error item are obtained;Trend item, seasonal item and residual error item are processed, and new training sample set is obtained;Cost prediction model is built, and the cost prediction model includes CNN residual module and bidirectional LSTM module, and new training sample set is input into cost prediction model to obtain predicted cost total amount;Error evaluation is carried out using cost total amount in test set and the predicted cost total amount, to evaluate the prediction performance of model.The present application improves the accuracy of cost intelligence accounting and the ability of capturing complex cost change characteristics.

This invention proposes a cost prediction method for 3D models of steel box girders based on reinforcement learning. It utilizes intelligent algorithms to deeply mine data from the 3D models of steel box girders, improving the accuracy and efficiency of cost prediction. The 3D model data of the steel box girder is preprocessed, converting the raw data into a standardized format and extracting multi-dimensional information such as geometric features, material properties, and structural complexity. A cost prediction model is constructed using a deep reinforcement learning algorithm. By optimizing the reward function and training strategy, the model can gradually approximate the actual manufacturing cost. The generalization ability and prediction accuracy are verified by comparing the model's prediction results with actual project data. Visualization tools are used to overlay the prediction results onto the 3D model, intuitively displaying high-cost areas and providing decision support for engineering design optimization and resource allocation. This method not only improves the accuracy of steel box girder manufacturing cost prediction but also provides a feasible technical solution for cost prediction of other complex structures.

The invention belongs to the technical field of consultation service management, and discloses a project cost consultation service management method and system, a terminal device and a storage medium, and the method guarantees data transparency and non-tampering through a block chain, assists intelligent decision making through AI, and finally achieves project cost consultation service in combination with an automatic process. Through AI intelligent auxiliary decision making and automatic process management, the service efficiency and decision making quality are remarkably improved, personal errors are reduced, factors such as material price fluctuation and construction difficulty are comprehensively considered through a cost prediction model, a high-precision budgeting scheme is generated, a manufacturing cost teacher is helped to quickly complete budgeting, and meanwhile, the cost prediction efficiency is improved. The automatic process module can automatically process tedious tasks such as contract approval, payment and settlement and the like, and the traditional work which needs several days or even several weeks is shortened to be completed within several hours, so that the labor cost is reduced, the project period is greatly shortened, and the overall business efficiency is improved.

This application relates to a method, system, and related equipment for engineering cost prediction based on MLP (Mechanical, Material, and Practical) estimation, belonging to the technical field of engineering cost estimation. The method includes: acquiring construction stage information of the target project, including the scheme study stage, preliminary design stage, and design expansion stage; acquiring construction variables for the corresponding construction stages based on the construction stage information; acquiring a preset MLP cost prediction model, which includes different quantities of engineering costs corresponding to different construction stages; and acquiring cost tables for different construction stages based on the construction variables and the MLP cost prediction model. This application has the effect of better displaying the cost changes that may occur during the project.

The invention is suitable for the technical field of road infrastructure maintenance management, and provides a cost prediction collaborative analysis method and system based on data analysis, and the method comprises the steps: obtaining a real-time collaborative cost element set of a specific road segment shielded by an upper structure, historical road segment data in a historical maintenance period, and corresponding maintenance records, screening historical maintenance samples consistent with the road section data in the preset maintenance period; extracting the historical deterioration degree of the specific road section in the historical maintenance sample, and taking the average value as the average deterioration degree of the specific road section in the preset maintenance period. Refined prediction of the maintenance cost of a specific road section shielded by an upper structure can be realized. The specific road section is divided into the air inlet section, the middle section and the air outlet section, the transverse air speed distribution and the evaporation rate difference are combined, the dry and wet state changes of all the sections are quantified, and the problem that in the prior art, local airflow disturbance and heterogeneous degradation are ignored, and consequently the cost prediction error is large is solved.

This invention is a method for scaling prediction of flow battery stack performance and cost based on single-cell data. First, performance data of laboratory single cells is acquired. Then, an area scaling factor is calculated based on target stack parameters to correct system auxiliary power consumption. Finally, a least-squares optimization inversion method is used to obtain the stack integration efficiency reduction factor. An extreme value statistical model of the full-lifecycle decay trajectory is used to determine the lifetime reduction coefficient, achieving accurate prediction of stack-level performance. Finally, the corrected performance parameters are input into a levelized energy storage cost model to achieve system-level economic prediction. This invention solves the problem of insufficient accuracy in predicting performance and cost from laboratory samples to engineering systems, establishing a complete cross-scale prediction system from materials to stack to system, providing reliable decision support for energy storage system planning.

This invention relates to the field of engineering cost prediction technology. Its purpose is to provide a method for constructing an onshore wind farm cost prediction model based on a Stacking ensemble machine learning model, addressing the problems of low accuracy or insufficient stability in existing wind farm cost prediction technologies. The technical solution can be summarized as follows: acquiring multi-dimensional historical data features of multiple prior construction projects, including at least the total investment per kilowatt; for any prior construction project, using the corresponding total investment per kilowatt as the target variable, and the remaining features forming a feature matrix as feature variables, integrating them into a single data sample to establish an original dataset containing multiple data samples; performing preprocessing; constructing a Stacking ensemble machine learning model, and training and testing it. The beneficial effect is that it improves the accuracy and versatility of the constructed model, making it suitable for onshore wind farm cost prediction.

The invention provides a mobile robot navigation safety reinforcement learning method, and belongs to the technical field of robot navigation based on reinforcement learning. The invention discloses a security reinforcement learning cost generation method in combination with a large language model, and aims to solve the problems of high difficulty and long time consumption of security reinforcement learning design constraint mathematics cost functions in the high-risk reality field. Through two core modules, the dangerous state action extraction network screens key unsafe data and inputs the key unsafe data into a large language model, interference is reduced, and time consumption is reduced; and the cost prediction module converts single and multi-constraint evaluation results of the large language model into quantitative cost, and the cost and a reward function are fused through a Lagrange multiplier method for strategy learning. According to the method, the mobile robot can learn a security strategy, the task effect is equivalent to that of traditional security reinforcement learning, the cost function design threshold is greatly reduced, the learning efficiency and security are improved, and the method can be widely applied to high-risk and resource-limited security reinforcement learning scenes.

The invention discloses a concealed conduit salt elimination project multi-objective optimization and cost prediction method and system, and the method comprises the steps: determining a soil hydraulic parameter, a water and salt migration parameter and a first prediction total cost, and carrying out the calculation of the first prediction total cost according to the soil hydraulic parameter, the water and salt migration parameter and the linear prediction cost; constructing a spatial topological feature, a water-salt dynamic feature and an economic cross feature; and inputting the spatial topological characteristics, the water-salt dynamic characteristics and the economic cross characteristics into a prediction model to obtain the underground pipe spacing, the pipeline diameter, the irrigation water amount and the prediction cost. The method solves the problems that an existing empirical model is difficult to accurately describe the nonlinear relation between parameters, actually measured data is scarce, area coverage is insufficient, and the generalization ability of the model is limited, the prediction precision is remarkably improved, multi-target collaborative optimization of the concealed conduit salt elimination project is achieved, and the design iteration period is shortened.

The invention discloses a cost prediction method and system applied to the smelting industry, and relates to the technical field of data analysis, and the method comprises the steps: setting a standard line of each aspect of content according to the characteristics of the various aspects of content; the standard line of each parameter of each aspect of content is comprehensively set by combining historical data, content characteristics of each aspect and smelting process simulation conditions, and a reliable basis is provided for subsequent stable conditions and unstable conditions and prediction. The difference between the standard line and the actual line of each aspect content is compared to distinguish a stable part and an unstable part on the actual line, and a prediction strategy is selected according to the unstable part, so that targeted prediction is performed, and the change condition of each aspect of the smelting process is better predicted. For abnormal conditions, additional cost is analyzed, comprehensive cost is calculated, the accuracy and adaptability of smelting cost prediction are improved, the management condition of the smelting cost is optimized, and efficient operation of smelting process tasks is guaranteed.

The present disclosure relates to a chemical flooding operation cost prediction method, comprising: determining the relevant factors of cost prediction; dividing the chemical flooding operation cost prediction stage according to the chemical flooding development stage; and establishing a staged principal component operation cost prediction model based on the relevant factors. The present method is a multi-factor classification, staged principal component operation cost prediction method based on motivation. Compared with the prior art, the present disclosure establishes a chemical flooding operation cost determination method based on the correlation analysis method between indexes based on the analysis of the factors affecting the operation cost and the mathematical statistics theory, and solves the subjectivity of human analysis of the main influencing factors. Meanwhile, the accuracy and reliability of the prediction results of the method have been verified by the actual oil field test, so that the cost trend prediction of different stages in the whole process of chemical flooding can be grasped.

The invention discloses a prediction data evaluation analysis method and system based on construction engineering cost, and relates to the technical field of intelligent data analysis, and the method comprises the steps: collecting multi-source heterogeneous data of construction engineering cost, carrying out the fusion through a multi-head attention mechanism, and generating a comprehensive cost feature vector; constructing a variational Bayesian neural network, outputting a cost prediction value and probability distribution according to the comprehensive cost feature vector, and calculating a confidence interval of the cost prediction value; and combining the risk thermodynamic diagram, the cost prediction value and the BIM model of the constructional engineering through MR interaction to generate a cost visualization view, and according to the change of the actual construction condition, adjusting the cost visualization view in real time through interaction with the cost visualization view, and evaluating the cost prediction value. According to the method, the network weight is parameterized through Gaussian variational distribution, point estimation of a traditional neural network is replaced, and quantification of prediction uncertainty is achieved.