28 results about "Delphi method" patented technology

The invention relates to a multi-agent-based bionic domain knowledge graph automatic construction method and system. The method comprises the following steps: constructing a bionic domain conceptual model; establishing a multi-agent system, and automatically extracting bionic entities and semantic relationships between the entities from an unstructured text; carrying out multi-dimensional collaborative verification on the extracted knowledge; based on a Delphi method consultation mechanism, collaborative decision making is carried out on verification results; and performing alignment and fusion on the verified knowledge to form a structured bionic domain knowledge graph. According to the method, three core technologies of a field fine-tuning multi-agent system, a multi-dimensional collaborative verification mechanism and Delphi method consultation decision are fused, so that automatic and high-efficiency construction of the bionic field knowledge graph is realized, and the generated knowledge graph has accuracy and comprehensiveness; the technical problems that a traditional construction method is low in automation degree and the knowledge accuracy is difficult to guarantee are effectively solved, and key knowledge infrastructure support can be provided for bionic theoretical research and technical innovation.

The invention relates to a method and a system for comprehensively evaluating and quantifying an aging transformation effect of an old community, and particularly belongs to the technical field of aging transformation evaluation. A three-dimensional model is constructed by fusing spatial, physical and environmental multi-source data through AR scanning and an algorithm, resident demands are extracted through natural language processing and a Delphi method, tags are matched and transformed, a multi-target scheme is optimized by adopting a simulated annealing algorithm, and a comprehensive index is calculated in combination with basic evaluation, investment benefits and property management coefficients. The system comprises five functional modules, achieves the precision and scientization of evaluation, effectively improves the rationality of a reconstruction scheme, and promotes the standardized development of the aging-suitable reconstruction industry of old communities.

The invention discloses an energy storage battery fault early warning method and system based on big data analysis, and relates to the technical field of big data analysis, and the method comprises the steps: collecting multi-source data, carrying out the preprocessing, extracting the features of the multi-source data, and constructing an input vector; setting an implicit state vector by using a Delphi method, and generating an input pair for prediction in combination with the input vector to obtain an optimal voltage prediction value; a compensation vector is constructed based on the optimal voltage predicted value, after independent MLP sub-networks are established for the positive electrode and the negative electrode of the energy storage battery respectively, the compensation vector serves as input, non-ideal voltage correction values under the positive electrode and the negative electrode are obtained, the optimal voltage predicted value is corrected, and a final correction voltage value is obtained; according to the method, the false alarm rate and the delay rate can be remarkably reduced, high-precision recognition and active early warning of early faults can be achieved in the energy storage field station-level application, and the system safety and the operation and maintenance efficiency are greatly improved.

This invention relates to a method for evaluating the energy-saving performance of green buildings based on a backpropagation (BP) neural network, belonging to the field of green building technology evaluation. Using the Delphi method and comparative analysis, 14 evaluation indicators are selected from five dimensions—energy-saving design, environmental energy consumption, building lighting, building ventilation, and building sunshine—to construct a quantitative indicator system. Then, the analogy-heuristic (AHP) method is used to determine the indicator weights, and consistency checks are performed to eliminate subjective bias. Finally, a BP neural network evaluation model is established, using the quantitative data of the 14 indicators as input. Through training and optimization, the energy-saving level of the green building is determined. This invention can accurately determine the indicator weights using a multi-dimensional quantitative indicator system and the AHP method, and it can ensure high accuracy of the evaluation results through the strong data processing and self-optimization capabilities of the BP neural network.

The invention relates to a Delphi consensus-based non-negative ridge regression risk sorting method and system, and the method comprises the following steps: 1) collecting expert scoring data based on a Delphi method, and constructing a scoring matrix containing post labels; 2) adopting K-means clustering in combination with nonparametric test, and extracting score divergence features; 3) constructing a sorting target variable, and introducing Gaussian disturbance to simulate score uncertainty; and 4) performing ridge regression modeling with non-negative constraint to obtain the sorting weight of each risk factor. According to the method, the stability and the organization suitability of a sorting result are improved, and the method is applied to a risk assessment scene in a complex engineering environment; the system is used for implementing the method. According to the method, the stability and organization suitability of the sorting result are improved, and the method is applied to a risk assessment scene in a complex engineering environment.

The invention provides an enterprise innovation ability portrait description method and device, electronic equipment and a medium, and relates to the technical field of data processing.The method comprises the steps that pre-acquired enterprise related information is preprocessed, and evaluation parameters are obtained; performing patent evolution technical index evaluation based on patent vectors over the years in the evaluation parameters, and mapping an evaluation result to obtain a cycle score; determining the word vector similarity of the first year of at least one companion enterprise, determining the word vector similarity of the second year according to the evaluation parameters, obtaining the companion cosine similarity between the enterprises based on the word vector similarity of the first year and the word vector similarity of the second year, and mapping the companion cosine similarity to obtain a similarity score; and on the basis of an interpretation framework constructed according to a Delphi method and a principal component analysis method, obtaining the enterprise innovation ability according to the evaluation parameters, the cycle score and the similarity score. According to the invention, the accuracy of the enterprise innovation ability portrait is effectively improved.

The invention discloses a cultural tourism economic operation data monitoring method, which comprises the following steps of: constructing a multi-dimensional value radar index system: establishing a multi-dimensional evaluation framework, and quantifying bridge and tunnel values; deploying a multi-source data acquisition network: constructing an integrated data acquisition system, and performing real-time mapping between a physical space and a digital space; and adaptive fusion analysis: constructing a quantum state superposition classifier, representing bridge and tunnel characteristics by using quantum bits, constructing a real-time digital twin mirror image engine, carrying out dynamic evaluation algorithm loading through linkage of a data acquisition network, a mirror image body and an algorithm pool, and introducing an ecological correction coefficient and a hidden value correction coefficient to carry out negative adjustment on an economic contribution value. Dynamically distributing an index weight by combining an entropy weight method and a Delphi method with a particle swarm optimization algorithm, and outputting an economic equivalent value in combination with the index weight; building a four-dimensional visual decision platform; and displaying the interactive radar map based on WebGL three-dimensional rendering and data binding technology.

The invention relates to the technical field of building heritage protection, and provides a railway building heritage protection method based on multi-source data fusion in order to solve the problems of data splitting, significant subjective deviation and decision staticization in the building heritage protection process. The method comprises the following steps: constructing a multi-dimensional digital file by comprehensively collecting a BIM model, an Internet of Things sensor network, a historical literature database and a geographic information system; establishing a hierarchical evaluation index system, setting an objective reference value, and determining the weight of a corresponding index by adopting a collaborative process integrating an analytic hierarchy process and a Delphi method; carrying out quantitative scoring through an expert team, and carrying out weighted calculation on a total score of a comprehensive value to determine a protection grade; and performing section division according to the spatial position, identifying regional dominant value features through clustering analysis, and generating a hierarchical protection strategy in combination with a protection rule base. According to the method, normal form conversion from subjective qualitative to objective quantitative in the evaluation process is realized, subjective deviation is remarkably reduced, and the accuracy and operability of protection decision making are improved.

The invention relates to the technical field of drug signal detection, in particular to a drug safety signal detection method, device and equipment and a computer storage medium. According to the method, a multi-dimensional quantitative evaluation system is constructed through a Delphi method and an analytic hierarchy process, systematic integration and scientific weighting are carried out on statistical signal strength, predictability, severity, report quality and preset AE events for the first time, and the limitation that a traditional method depends on a single statistical index is overcome. By introducing a preset AE list and combining a traditional DPA method, the defect of missing detection of rare and serious signals by a traditional threshold rule is made up. And predictive intelligent judgment is realized by utilizing a large language model, so that the report processing efficiency is improved. By incorporating severity and report quality into an evaluation system, the credibility layering capability of the signal is enhanced. Finally, by integrating all dimension attributes and applying a dynamic weight system to carry out priority ranking, a risk signal list is generated, and the accuracy and timeliness of drug safety monitoring are improved.

The invention discloses a teaching process evaluation and accurate intervention method and system based on ability portray.The method belongs to the technical field of wisdom education, and the method comprises the steps that full-dimensional teaching data containing teacher and student recessive states are collected through a multi-source heterogeneous architecture, and refined preprocessing is carried out; a cognitive load theory and a multivariate intelligence theory are fused to construct a student multi-dimensional cognitive load label library and a behavior semantic unit chain model, a Delphi method and an analytic hierarchy process are combined to construct a teacher teaching ability index system, and a teaching and learning two-way linkage mapping model is established; an improved multi-modal deep learning fusion model and a transfer learning model are used for accurate evaluation, and based on an evaluation result and real-time data, hierarchical personalized intervention suggestions are generated and dynamically adjusted through an improved decision tree and reinforcement learning. The problems that existing teaching evaluation is one-sided, intervention lags behind, linkage lacks and the data security risk is high are solved, and the objectivity of teaching evaluation and the timeliness of teaching intervention are remarkably improved.

This invention provides a method and system for optimizing the deployment of nearshore fisheries resource monitoring stations and navigation routes based on multiple objectives. The invention first determines the optimization objectives, then selects the optimal coupling model through evaluation indicators, and obtains the true distribution data of resource density through the optimal coupling model. It employs the Delphi method combined with information entropy and coefficient of variation as dual objective weights, along with a target-oriented correction coefficient, to obtain the dynamic weights of the optimization objectives. Three-level dynamic stratified sampling is performed using a heterogeneity threshold, and the optimal number of stations is determined through precision-cost elasticity analysis. Finally, a multi-objective optimization function is constructed, integrating navigation distance, fuel cost, and operational time matching. The optimal navigation route is solved using SA-PSO. This invention effectively solves the problems of systematic bias and insufficient resource adaptability in traditional surveys, significantly improves sampling representativeness and navigation operation efficiency, reduces survey costs, and can be dynamically adjusted according to resource conservation and fisheries production needs.

The application discloses a risk control system and method for a financing guarantee industry, wherein an industry evaluation index system table module reduces the dimension of qualitative indexes, and a support vector machine model adopting recursive feature elimination is used to reduce the dimension of quantitative data to screen important indexes; a risk assessment model module adopts a multilayer Delphi method module to determine the weight of each index, sets an alarm signal, and sets a risk threshold of each index according to an industry standard; a risk value module is used to obtain each index value through a user input mode, and each business link risk value is calculated according to the risk assessment model module; a penalty factor module performs a credit rating prediction, and determines a credit rating binding penalty factor; and an early warning mechanism module monitors the system through an early warning task, triggers early warning monitoring according to early warning rules after a risk result is obtained, and performs early warning display. The application can effectively improve the risk control capability of a guarantee company.

The invention relates to the technical field of data processing, in particular to a smart campus service maturity assessment method based on dynamic weight and multi-modal data, and the method comprises the steps: collecting multi-modal data including educational activities, mental health, campus point cloud atlas and security events, and IT service capability, and carrying out the preprocessing to form a standardized assessment data set; constructing a six-dimension evaluation index system, determining an initial weight by combining a Delphi method with an analytic hierarchy process, and dynamically adjusting the weight based on a knowledge graph and an LSTM neural network; a feature level and decision level mixed fusion strategy is adopted for evaluation, dimension scores are calculated, and maturity levels are divided; and visually analyzing an evaluation result, generating a report containing resource configuration suggestions, and combining feedback to optimize a management strategy. According to the method, the problems of single evaluation data, fixed weight and insufficient practicability in the prior art are solved, accurate evaluation and dynamic optimization are realized, and support is provided for campus resource allocation and policy adjustment.

The invention discloses a construction method of a drug clinical test quality risk prediction model, and belongs to the technical field of clinical test management and artificial intelligence. The method comprises the following steps: firstly, constructing an initial risk index set based on laws and regulations and expert knowledge, and performing multiple rounds of expert investigation by adopting a Delphi method in combination with statistical test according to a high score greater than or equal to 0.7 and a variation rate lt; screening out a high-level consensus index set according to 25% consensus standards; then large-scale questionnaire survey is carried out, and the collected data is subjected to trust-validity test; taking the verified data as a training set, carrying out feature importance sorting by adopting a regression algorithm of machine learning, and screening out key risk indexes; and finally, training by taking the key indexes as characteristics and taking superior indexes as target variables to obtain a series of risk prediction models. According to the method, objective and quantitative evaluation and accurate prediction of clinical test quality risks are realized, and scientific data-driven decision support can be provided for derivation of quality tolerance and optimization of risk management plans.

The invention discloses a power business and 5G communication network suitability analysis method, which comprises the following steps: constructing a three-layer grading evaluation system comprising technical class, economic class and development class indexes, adopting a Delphi method in combination with an analytic hierarchy process to determine the index weight of each layer, and carrying out quantitative scoring on the indexes based on power business requirements and 5G technical parameters; a multi-level weighted summation model is utilized to calculate a comprehensive adaptation degree score under each service scene, and then an adaptive 5G network slice type is recommended according to a scoring result. According to the invention, systematized and quantifiable evaluation of the power business and 5G communication capability is realized, the scientificity and intelligence level of resource allocation are improved, and the method is suitable for differentiated communication demand matching of various businesses such as inspection, metering, video and control in a smart power grid.

The invention discloses an urban residential district infrastructure system toughness evaluation method, which comprises the following steps: S1, decomposing the toughness of an urban residential district infrastructure system into a plurality of toughness dimensions according to the components of the urban residential district infrastructure system; s2, dividing the toughness period into a plurality of toughness stages according to historical research data; s3, according to the historical data, obtaining a toughness influence factor from the aspects of a toughness stage, a historical toughness index, a regional disaster type, a regional policy and regional management; s4, performing rationality and practicability screening on the toughness influence factors by adopting a Delphi method to obtain screened toughness influence factors; s5, constructing a toughness evaluation index system, and constructing a toughness evaluation algorithm model based on an entropy weight method; and S6, inputting the initial values of the screened toughness influence factors into the toughness evaluation algorithm model, and outputting a toughness evaluation result. According to the method, toughness evaluation of the urban residential area infrastructure system is realized, and the preciseness of quantitative toughness index selection and the pertinence of toughness analysis are improved.

The invention discloses a power battery industry chain dynamic quality map construction method and system based on an analytic hierarchy process and Delphi weight fusion. The method can solve the problems that due to the fact that policy requirements, standard specifications and enterprise performance data are disjointed, measurement criteria are missing, compliance evaluation efficiency is low, and subjectivity is high. Firstly, policies, standards and enterprise data are analyzed through a natural language processing technology, and a structured data pool is formed; then, an analytic hierarchy process is combined with a Delphi method, and comprehensive weights of policy compliance, standard universality and industrial authenticity are determined; calculating the comprehensive deviation degree of each quality index based on the weight, and carrying out risk evaluation; and finally, constructing a dynamic visual quality map by using a graph database technology, and realizing highlighting and correlation analysis of risk nodes. According to the method, quantitative fusion and dynamic early warning of'requirement-specification-expression 'are realized, the efficiency can be improved by 40-60 times, the compliance risk cost is reduced by 15-30%, and the automation and decision scientificity of industrial chain quality control are remarkably enhanced.

The application discloses a kind of for the establishment method and device of evaluation system of children swimming, wherein method includes obtaining research questionnaire from equipment end, wherein the research questionnaire includes the feedback content for each index in initial index system;Based on the feedback content, the initial index system is adjusted using the preset Delphi method and the preset analytic hierarchy process to determine the target index system;The measured data of children swimming is obtained, to optimize the target system based on the measured data. By this way, the construction of index system is limited to the influence of expert subjective factors, and the defects of being limited to rely on a large number of data construction are overcome.

The invention discloses an automobile maintenance industry prosperity index construction method based on multi-source data fusion. The method comprises the following steps: collecting monthly index data of an automobile maintenance industry; screening the monthly index data to obtain screened monthly index data; converting the screened monthly index data into index diffusion indexes of five dimensions; carrying out weight distribution on the indexes of the five dimensions based on an improved Delphi method, and calculating the business index of the automobile maintenance industry according to the distributed weight and the corresponding index diffusion index; according to the method, related data are collected in combination with five dimensions, the automobile maintenance industry condition index capable of dynamically monitoring industry condition changes is constructed, and a quantitative basis is provided for automobile maintenance enterprise operation decision making, investment planning and government policy making.

The invention discloses a method for demarcating a groundwater reserve area. The method comprises the steps of information atlas construction, overlay analysis and optimization adjustment. Key indexes are screened through single-factor analysis, a vector diagram is drawn, and the vector diagram is rasterized through a Delphi method; and determining a weight by using an analytic hierarchy process, overlapping and screening an optimal region, and optimizing a delimiting result in combination with a hydrogeological unit and an administrative region. According to the method, the problems of single evaluation dimension, high subjective dependence and incomplete technical path in the prior art are solved, scientific and systematic accurate demarcation of the underground water reserve area is realized, and the method has wide popularization and application values.

The invention relates to an evaluation method and system for the post value of a fair hospital, and belongs to the technical field of data processing, and the method comprises the following steps: building a post value evaluation index library: building an index library of medical treatment, medical technology, nursing, management, guarantee and scientific research sequences; establishing a post value evaluation expert team corresponding to each sequence; constructing an evaluation index system and determining weights: applying a Delphi method and an entropy weight method, and determining objective weights of the indexes through expert letter selection of the system containing quantitative and qualitative indexes; performing post value pre-evaluation and formal evaluation: randomly selecting 30% of expert demonstration systems and weights in pre-evaluation, performing formal evaluation if the system and the weights conform to reality, organizing 100% of experts to perform evaluation in batches and in sequence, and calculating a final score; dividing post value grades; determining a post value coefficient; and applying the evaluation result. The method has the advantages that post value pre-evaluation and official evaluation are carried out, so that post responsibility and technical labor service value of medical staff are reflected, and public welfare attributes of fair hospitals are highlighted.

The application discloses a kind of aircraft rush / cause runway event risk early warning and cause identification method and system, method includes: S0: by FOQA standard, SOP and QRH obtains the key parameter set and risk factor set of rush cause runway event;S1: based on the correspondence of key parameters and risk factors is constructed by Delphi method;S2: construct the rush cause runway risk prediction model based on Transformer, realize online risk identification;S3: based on hypothesis testing method obtains the most similar cause, completes risk factor identification.

The application provides an insurance data-driven accident-hidden danger correlation analysis and hidden danger weight calculation method, which comprises the following steps: according to the correlation characteristics of hidden dangers and accidents, the accidents are divided into three categories, namely direct hidden dangers, emergency hidden dangers and comprehensive hidden dangers related to emergency hidden dangers; the Delphi method is used to make binary determination on the correlation of hidden dangers and accidents one by one, and an accident-hidden danger correlation matrix is established; based on the safety production liability insurance policy data, the frequency correlation index, the loss correlation index and the weight calculation method of the three types of hidden dangers are established by comprehensively considering the accident-hidden danger correlation matrix and the risk index calculation results, and the importance of different hidden dangers to accidents is quantitatively obtained; based on the mapping relationship between accidents and hidden dangers and the weight values of different hidden dangers, the frequency prediction index and the loss prediction index of different types of accidents are calculated according to the hidden danger elimination data, and the dynamic risk evaluation of different types of accidents is realized. The application can provide a scientific basis for hidden danger elimination and accident prevention in different industries and improve the safety production guarantee capability.

The application discloses a method for constructing a neonatal intensive care unit medical related infection evaluation and grading system by using the Delphi method, and belongs to the technical field of medical quality management. The method comprises the following steps: establishing a multidisciplinary research team; determining candidate indexes through systematic literature retrieval; carefully selecting and recruiting experts; designing an expert consultation questionnaire containing outcome indexes, process indexes, balance indexes and sentinel indexes; carrying out two rounds of Delphi expert consultation, and organizing online expert meeting to discuss uncertain indexes during the two rounds of Delphi expert consultation; adopting SPSS software to analyze data, and calculating the authority coefficient of experts, the group median and the divergence index; and finally determining the NICU-Shield evaluation system, which contains 11 core indexes (3 outcome indexes, 6 process indexes and 2 balance indexes) and 1 sentinel index. The application constructs a quality evaluation and grading system specially for neonatal intensive care unit medical related infections.

This invention discloses a sound barrier scheme selection method based on a novel distance metric, comprising: determining the classification criteria for the barrier material; consulting with experts using the Delphi method to determine the effectiveness of existing sound barriers; determining the evaluation indicators of the secondary indicator layer of the hierarchical evaluation index system for sound barriers after multiple rounds of expert consultation; and objectively assigning information entropy as a weight based on the original numerical dispersion of the secondary indicator layer evaluation indicators to quantify the evaluation indicators and form a weighted standardized decision matrix Q. γ According to the weighted standardized decision matrix Q γ The final relative proximity score and final normalized result are obtained sequentially, and the sound barrier scheme is evaluated based on the final normalized result. The sound barrier scheme selection method of this invention has advantages such as solving the problem of relying on subjective expert weighting, overcoming the limitation that Euclidean distance cannot determine the merits of a scheme, compensating for the defects of judgment failure, and improving the objectivity of indicator weights.

The invention discloses a multi-level index talent comprehensive review method and system, and belongs to the technical field of human resource management, and the method comprises the following steps: 1, determining a review index system: constructing a multi-level review index system comprising first-level indexes, second-level sub-indexes and corresponding weights, wherein the first-level indexes at least cover a professional skill index, a comprehensive quality index and a working experience index, and the weights of the first-level indexes and subordinate second-level sub-indexes are determined through an analytic hierarchy process or a Delphi method; step 2, talent data collection: a resume screening module, an interview evaluation module, a skill test module and a work achievement verification module are used for collecting original data corresponding to review indexes; a multi-level evaluation index system comprising first-level indexes, second-level sub-indexes and corresponding weights is constructed, core dimensions such as professional skills, comprehensive quality and working experience are covered, the problems that traditional evaluation indexes are single and talents are difficult to comprehensively evaluate are solved, and all-around and multi-dimensional evaluation of the talents is achieved.

The invention provides a firework and cracker production and sales whole process risk factor analysis model construction method, which comprises the steps of establishing a business process preliminary analysis framework and business process analysis factors, and listing risk subsystems and risk factors; a TF-IDF algorithm is used to extract the risk factors, and through similarity calculation, seed factors required by model construction are obtained; performing iterative divergence on the seed factors by adopting literature data, and performing divergence by an expert group Delphi method to achieve risk factor expansion so as to form a convergence factor set; adopting a DM-AHP hybrid algorithm to carry out secondary Delphi method operation on the confluence factor set, and endowing each element in the factor set with a weight; establishing hierarchical holographic modeling, and displaying related factors of the risk system for the factor set endowed with the weight data; risk factors of a risk system are analyzed from a mesoscopic level, modeling is performed by using a main logic diagram in a microscopic level, and a risk factor analysis subsystem is established. According to the method, risk factors are analyzed from the whole firework and firecracker production and sales process, and overall system analysis is facilitated.

The invention relates to the cross technical field of intellectual property value quantitative evaluation and high-tech policy orientation, in particular to a patent feature vector processing method and system, and the method comprises the steps: constructing a six-dimensional feature vector template covering the high-tech adaptability of a legal technical economic market strategy; a model evaluation process is executed to collect full life cycle data of a patent, through AHP expert scoring in combination with a triangular membership function and minimum-maximum normalized formula quantitative calculation, during dynamic weight determination, an NLP analysis policy, a Delphi method integrated expert experience and random forest model training are utilized, and the weight is hot-updated after Softmax normalization, threshold detection and policy correction. The method comprehensively covers the multivariate values of patents, dynamically adapts to high-tech development requirements, improves the evaluation accuracy and scientificity, provides reliable support for patent operation and innovation decision-making, and is suitable for patent technology economic potential score evaluation scenes in various fields.