45 results about "Fuzzy linguistic" patented technology

The invention provides a control method based on differential rotation speed torque distribution, which relates to the technical field of intelligent control and comprises the following steps: performing difference calculation on an initial input quantity and a preset rotation speed instruction to generate a rotation speed deviation signal and a deviation change rate, and establishing a dynamic membership function library through a fuzzy controller; mapping the rotating speed deviation and the change rate thereof into a fuzzy language variable, performing reasoning operation according to a preset fuzzy control rule base, and outputting a frequency regulation quantity and a torque compensation coefficient of the frequency converter; and reading the generated torque compensation coefficient and shaft system torque values actually measured by the two torquemeters, calculating a dynamic difference value between the current total load torque and the target torque, establishing a torque distribution weight model according to the transmission characteristics of the differential mechanism, and generating differential torque correction instructions of the two motors in combination with the real-time rotating speed values. The control performance of differential drive is improved.

The invention provides a JKW control method based on adaptive fuzzy control, which belongs to the technical field of reactive power compensation of a power system, and comprises the following steps of: interacting reactive power compensation states of JKW devices in adjacent regions based on an edge physical agent, constructing a regional reactive power topological graph in combination with local power grid topological data, generating a regional coordination instruction according to a supply-demand relationship, and establishing a regional coordination graph according to the regional coordination instruction; the method comprises the following steps: acquiring proportion deviation, power factor deviation and reactive power change gradient of a mutual inductor, constructing a standard fuzzy input vector in combination with a regional cooperation instruction, mapping the standard fuzzy input vector into a fuzzy linguistic variable through a dynamically updated fuzzy rule base, and reasoning and outputting an initial switching strategy; and comparing and analyzing the proportion deviation and the power factor deviation through a hardware comparator, determining a trigger condition and existence of a fault, and dynamically optimizing an initial switching strategy by combining a regional reactive topological graph to realize the control of the JKW. And the operation stability of the power grid is obviously improved.

The invention discloses a spiral anchor foundation grouting pressure-flow-deformation intelligent coupling control method, and relates to the technical field of foundation grouting technologies, and the spiral anchor foundation grouting pressure-flow-deformation intelligent coupling control method comprises the steps that according to specification parameters of a spiral anchor and the type of a soil body where the spiral anchor is located, a preset engineering parameter set is matched; collecting grouting data of each grouting channel, and calculating grouting deviation data in combination with the engineering parameter set; performing fuzzification processing on the grouting deviation data, and converting the grouting deviation data into fuzzy linguistic variables; inputting the fuzzy language variable into a preset fuzzy rule base for reasoning, and outputting a PID parameter correction amount; parameters of a PID controller are dynamically adjusted according to the correction amount, and a pump speed adjusting instruction is generated; executing the pump speed adjusting instruction, and collecting grouting data after execution; a soil body permeability coefficient is obtained through inversion by constructing a digital twinborn model, and the fuzzy rule base is optimized and updated by combining the executed grouting data. The method is used for solving the problem that a traditional spiral anchor foundation grouting technology is poor in adaptability to complex geology.

The invention discloses a multi-scheduling scheme decision-making method and device based on hesitant fuzzy information and a multi-attribute group decision-making theory in the technical field of power grid power generation optimization scheduling. The multi-scheduling scheme decision-making method comprises the following steps: determining a plurality of attribute indexes influencing a power grid power generation scheduling scheme according to the power grid power generation scheduling scheme; performing quantitative processing on each expert evaluation information matrix based on a preset computable hesitant fuzzy language term set to obtain a quantitative data decision matrix; calculating the positive separation degree and the negative separation degree of quantized data corresponding to each power grid power generation scheduling scheme based on the positive ideal point and the negative ideal point of each quantized data decision matrix; and calculating the progress of each power grid power generation scheduling scheme, and selecting the power grid power generation scheduling scheme corresponding to the maximum progress as the optimal scheduling scheme. The method has the advantages that the positive ideal solution and the negative ideal solution can be determined according to the group decision evaluation information, the relative schedule of each scheduling scheme is calculated, the evaluation scheduling schemes are sorted and preferentially selected, and the problem that the decision schemes are difficult to achieve consistency is effectively solved.

The invention discloses a park micro-grid energy prediction and correction method based on a fuzzy language function. According to the method, a park micro-grid photovoltaic power generation capacity is taken as a prediction target, illuminance, temperature and air visibility are taken as core indexes to construct a park micro-grid photovoltaic power generation system prediction model, and the characteristics of high calculation speed and high responsiveness of a fuzzy language function are creatively utilized to track system prediction errors and error change rates. Core parameter indexes of the model are corrected in real time after fuzzy reasoning calculation, so that the model always tracks real-time environment characteristics to realize evolution, the park microgrid energy state is effectively predicted, a basis is provided for power dispatching and the like of the whole system, the charging and discharging time sequence of an energy storage system is guided, and the energy efficiency is improved. Therefore, a scientific solution is provided for the problem.

The invention discloses a precise sensing control method for the combustion state of an internal combustion engine. The method comprises the steps that S1, parameters are collected; s2, establishing a neural network model, training the neural network model, and identifying the running state of the internal combustion engine; s3, a fuzzy language is established, and respective fuzzy adjustment amounts of a fuel injection system, a valve transmission system and an ignition system are obtained; s4, self-adaptive control models of the fuel injection system, the valve transmission system and the ignition system are established respectively, and the self-adaptive adjustment amount of the fuel injection system, the self-adaptive adjustment amount of the valve transmission system and the self-adaptive adjustment amount of the ignition system are obtained; and S5, carrying out weighted fusion on the fuzzy adjustment amount and the adaptive adjustment amount to obtain a final adjustment amount. By collecting multi-dimensional operation parameters in real time, extracting time domain and frequency domain features and combining a deep neural network model, precise recognition and early warning of the operation state of the internal combustion engine are achieved, detection and response can be made in time when the working condition of the internal combustion engine changes slightly, and the problem that a traditional control system is lagged in response is solved.

The invention relates to the technical field of ownership intelligence, in particular to a ownership intelligence fuzzy language instruction recognition method based on scene risk guidance. In order to solve the problem that a fuzzy language instruction recognition method in the prior art easily causes understanding deviation and potential safety hazards, the invention provides an intelligent fuzzy language instruction recognition method based on scene risk guidance, which comprises the following steps of: 1) constructing a scene risk map according to a basic risk and a distance risk; 2) identifying an instruction type; 3) instruction analysis and risk assessment; and 4) instruction rewriting and object identification replacement. According to the method, a risk perception mechanism is introduced, the high-risk behavior execution probability caused by semantic deviation of the intelligent robot is effectively reduced, the understanding accuracy and interaction safety of the intelligent robot in a real scene are improved, and the method is suitable for a complex application environment with high requirements for task reliability and behavior controllability of the intelligent robot.

The invention relates to the technical field of granulation control, and discloses a powder granulation control method and system based on fuzzy control, the system comprises a data acquisition unit, a data processing unit, a data analysis unit and a data adjustment unit; by collecting key parameters such as powder humidity in real time, instant and accurate data are provided for control; through fine processing such as filtering, normalization and feature extraction, data noise is removed, the data scale is unified, and parameter dynamic change features are deeply mined; by means of a preset fuzzy rule, the parameter features are converted into fuzzy linguistic variables for reasoning, and the equipment adjustment amount can be scientifically and reasonably determined; in the execution link, a final adjustment value is determined through weighted average, and precise regulation and control of the granulation equipment are achieved; the rich and practical fuzzy rule base covers various parameter deviation combinations, so that the system can adapt to different granulation working conditions, and the granulation efficiency and the product quality are effectively improved.

The invention discloses a vacuum exhaust throttle valve setting method and system. The method comprises the steps that the current pressure value in a vacuum pipeline is obtained; calculating a pressure deviation and a pressure deviation change rate according to a preset target pressure value and the collected current pressure value; fuzzifying the calculated pressure deviation and the pressure deviation change rate to obtain a corresponding fuzzy linguistic variable; performing fuzzy reasoning based on a preset fuzzy rule base to obtain a valve opening adjustment amount in a fuzzy form; performing defuzzification processing on the valve opening adjustment amount in the fuzzy form to obtain an accurate valve opening adjustment amount value; and the opening degree of the exhaust throttle valve is adjusted according to the accurate valve opening degree adjustment amount value. The opening degree of the exhaust throttle valve is dynamically adjusted, and rapid and accurate control is achieved.

The embodiment of the invention provides an intelligent bone drilling self-adaptive control method for a mechanical arm, which comprises the following steps: acquiring displacement deviation of the tail end of a drill bit of an orthopedic surgical robot, obtaining an error change rate through differential calculation, and combining a bone layer type as an input variable of a fuzzy controller and a feeding speed as an output variable; input variables are fuzzified through a membership function, and a fuzzy language variable set is obtained; according to the set and a preset rule base, constructing a multi-rule group structure comprising three types of scenes of free space, cancellous bone and cortical bone, and setting corresponding fuzzy rule subsets for different bone layers; designing a ''minimum-maximum'' rule activation and combination strategy for reasoning by adopting a Mamdani type fuzzy reasoning method according to fuzzification input and a multi-rule group structure, and generating a fuzzification output variable set; and defuzzification is performed through a gravity center method to obtain a continuous speed instruction, and dynamic regulation and control of the drill bit feeding speed are achieved. When approaching a penetration point, the device automatically decelerates and safely stops, so that the safety and accuracy of an operation are effectively guaranteed, and over-drilling injury is prevented.

The invention discloses a hazardous chemical substance transportation early warning system based on a fuzzy neural network, and relates to the technical field of traffic transportation and road safety monitoring. According to the hazardous chemical substance transportation early warning system based on the fuzzy neural network, road geometric influence in original data of a sensor is accurately stripped from dynamic response of a vehicle; according to the method, false risk signals caused by road design can be eliminated, the method focuses on instability risks really caused by dynamic factors such as vehicle control and load transfer, and the rollover risk can be judged more essentially and more accurately; converting the preprocessed characteristic quantity into a fuzzy linguistic variable, reasoning by simulating a fuzzy rule of human expert experience, and finally outputting continuous risk indexes and levels; the processing mode not only better conforms to the imprecise characteristic of risk assessment, but also enhances the adaptability and robustness of the system to different vehicle types, loads and road conditions.

The invention discloses a medicine cold-chain logistics enterprise recommendation method based on a Fermat fuzzy set. The method comprises the steps of obtaining a transportation quality data set of a plurality of alternative logistics enterprises under evaluation indexes; constructing an expert evaluation matrix through the Fermat fuzzy linguistic variables, and evaluating the importance of experts through the Fermat fuzzy linguistic variables so as to determine the weight of each expert; giving a language evaluation matrix through a Fermat fuzzy language variable and converting the language evaluation matrix into a Fermat fuzzy number; obtaining a Fermat fuzzy group evaluation matrix based on the expert weight and a Fermat fuzzy Einstein interactive integration operator, and performing standardization; based on a Fermat fuzzy set score function and an Einstein interactive integration operator, objective and subjective weights of evaluation indexes are obtained through a Fermat fuzzy variable coefficient method and a Fermat fuzzy step-by-step weight evaluation ratio analysis method respectively, and then a comprehensive index weight is obtained; and according to a Fermat fuzzy set-based scoring function and an Einstein integration operator, obtaining a sequence through an improved comprehensive compromise solution method so as to determine an optimal enterprise.

The invention relates to the technical field of agricultural information, in particular to a product supplier and consumer matching method and system based on information axiom, and the method comprises the steps: recognizing the attributes of agricultural products; defining a system range and a design range for each attribute; for each matching scheme between the consumer and the supplier, checking whether all hard attributes are met or not, and if not, filtering out the matching scheme; for the soft attributes, calculating the information amount from the perspective of consumers and the perspective of suppliers: for the quantitative soft attributes, calculating the information amount according to the types of the quantitative soft attributes; for qualitative soft attributes, applying a fuzzy mathematical method, and then calculating information amount; respectively calculating the total information amount of the consumer perspective and the total information amount of the supplier perspective; establishing a multi-objective optimization model; for all possible matching schemes, calculating the total information amount of consumers and suppliers, and determining respective maximum values and minimum values; for each matching scheme, calculating a normalized membership function value by comparing the total information amount with the maximum value and the minimum value of all the matching schemes; the matching scheme enabling the weighted comprehensive score of the membership function to be the highest is selected. The invention provides an intelligent matching method which can comprehensively consider unique attributes, dynamic transaction demands and fuzzy language features of agricultural products, so as to optimize supply and demand matching and promote agricultural product sales and sustainable economic development.

The invention discloses a lithium battery assembly risk analysis method. The method comprises the following steps: S1, evaluating the severity, occurrence frequency and detection degree of a failure mode in lithium battery assembly by using a double-layer hesitant fuzzy language term set; wherein the double-layer hesitant fuzzy language term set comprises a double-layer language term set and a hesitant fuzzy language term set, and the double-layer language term set and the hesitant fuzzy language term set are both composed of evaluation information of evaluation personnel; s2, calculating an evaluation personnel weight based on similarity measurement, and calculating influence factor weights of severity, occurrence frequency and detection degree based on a water injection principle; s3, aggregating evaluation information of evaluation personnel by adopting a combined compromise sorting method, and calculating a failure mode risk value; s4, determining optimal evaluation information through a multi-target aggregation technology; according to the method, the main layer expresses basic semantics and the auxiliary layer modifies the degree, so that the effects of accurately describing the risk degree and avoiding misjudgment of an extreme value are achieved. Meanwhile, the semantic constraint rule is used for eliminating logic conflicts and improving the expression efficiency.

Methods for determining the reliability of a technical system using fault tree analysis, comprising the following steps: S1 - Defining basic events of fault tree analysis; S2 - for each basic event, defining a fuzzy linguistic variable and a set of membership functions; S3 - at least partially based on real-time embedded software, defines a minimal cutting set for linguistic fault tree analysis; S4 - at least partially based on the minimum intersection theorem, determining the reliability of the technical system. Furthermore, the invention relates to a control unit, vehicle system, a computer program product and a computer-readable medium for executing the method.

This invention discloses a risk analysis method for lithium battery assembly, comprising the following steps: Step S1, using a two-layer hesitant fuzzy language terminology set to evaluate the severity, frequency of occurrence, and detectability of failure modes in lithium battery assembly; wherein, the two-layer hesitant fuzzy language terminology set includes a two-layer language terminology set and a hesitant fuzzy language terminology set, both composed of evaluation information from evaluators; Step S2, calculating evaluator weights based on similarity measures, and calculating the influencing factor weights of severity, frequency of occurrence, and detectability based on the principle of water injection; Step S3, aggregating the evaluation information of evaluators using a combined compromise ranking method to calculate the failure mode risk value; Step S4, determining the optimal evaluation information through multi-objective aggregation technology; This invention accurately describes the degree of risk by expressing basic semantics at the main layer and modifying the degree of modification at the sub-layer, thus avoiding misjudgment of extreme values. Simultaneously, semantic constraint rules are used to eliminate logical conflicts and improve expression efficiency.

According to the group decision-making method based on the leader-follower dynamic game, a leader-follower hierarchical adjustment rule is designed to carry out iterative adjustment on an expert evaluation matrix, control and stability of a leader on a decision-making direction are guaranteed, bidirectional optimization is formed through feedback of the follower, and the decision-making efficiency is improved. The authority and the democratic are effectively coordinated, the group consensus degree is remarkably improved, the number of iterations is reduced, and the consensus achievement efficiency is improved. The method comprises the following steps: S1, collecting an evaluation matrix expressed by experts to hesitate a fuzzy language term set; s2, clustering experts through distance measurement and determining intra-class and clustering weights; s3, calculating multi-layer consensus degree to measure and evaluate consistency; s4, if the group consensus degree does not reach the preset threshold value, iteratively adjusting the expert evaluation matrix according to a hierarchical adjustment rule until the expert evaluation matrix reaches the standard; and S5, sorting the schemes by using an approximate positive and negative ideal solution.

The invention discloses an integrated decision-making method for evaluating the digital transformation capability of a logistics enterprise, and the method comprises the steps: constructing an evaluation index system comprising a plurality of dimensions according to the digital transformation characteristics of the logistics enterprise; evaluation information is given according to the evaluation index system and the candidate logistics enterprises for evaluation to obtain evaluation data; expressing evaluation preferences by using linguistic variables in a spherical fuzzy set, and converting the linguistic variables into spherical fuzzy numbers; determining an evaluation weight through a spherical fuzzy score function; fusing the evaluation information by using a spherical fuzzy Sugeno-Weber priority operator to generate a comprehensive evaluation matrix; in combination with an SPC model and an SWARA method, comprehensive weights of evaluation indexes are determined from objective and subjective perspectives; and sorting the candidate logistics enterprises by using a spherical fuzzy regret AROMAN method, calculating a comprehensive score of each candidate enterprise through an ideal point vector and a regret matrix, and finally determining priorities of the candidate logistics enterprises. According to the method, the uncertainty of the evaluation process can be comprehensively and accurately reflected, and extraction and recommendation can be carried out.

The invention discloses a weight-adaptive multi-scene energy storage power station participation frequency modulation contribution degree evaluation method, which comprises the steps of establishing a multi-dimensional index model of an energy storage power station in a frequency modulation scene, determining an initial weight of the established index model by adopting a hesitant fuzzy language-cloud model, and calculating the frequency modulation contribution degree of the energy storage power station according to the frequency deviation of an actual system. And determining an adaptive weight coefficient to adjust a weight system, and evaluating the contribution degree of participation in frequency modulation of the energy storage power station based on a PROMETHEE-II evaluation method improved by TODIM. The evaluation method can scientifically quantify the actual contribution of the energy storage power station participating in the power grid frequency modulation in different scenes, and provides an important basis for the energy storage power station participating in the power grid frequency modulation scheduling strategy and establishment of an incentive mechanism of an auxiliary service market.

The application provides a medical data-oriented deep convolution fuzzy neural network and a training method thereof, and comprises a medical data explainability prediction model (IP-DCFNN) based on a deep convolution fuzzy neural network. The IP-DCFNN is composed of three parts: a fuzzy logic antecedent part, a deep convolution calculation part and a fuzzy result representation part. The fuzzy logic antecedent part extracts input data, and the input data is converted from a numerical value into a set of membership degree values for fuzzy language scalars through the operation of a membership function in the fuzzy logic antecedent part. The deep convolution calculation part extracts hidden features in input rule weights, and converts hidden layer weights into high latitude information representation. The fuzzy result representation part is used to process the defuzzification process in fuzzy reasoning. The application relates to the technical field of computer technology, and the IP-DCFNN adds the concept of a deep convolution neural network on the basis of a fuzzy reasoning system to achieve the explainability prediction capability for medical data.

The application discloses a kind of nuclear power equipment value chain manufacturing risk assessment methods.The present application determines risk group and risk factor in nuclear power equipment manufacturing from risk database;Adopt hesitating fuzzy language term set method, define a set of risk grade evaluation language set, define semantic function as conversion standard;According to risk group, risk factor and risk grade evaluation language set, obtain the evaluation information of each nuclear power equipment value chain manufacturing risk factor from risk database;The evaluation information is converted into triangular fuzzy number and aggregated, the risk importance and risk grade of each risk factor and risk group are determined, and the overall risk importance and risk grade are determined.The present application effectively and accurately processes fuzzy information in risk assessment, comprehensively analyzes the risk importance of each risk factor and risk group, and provides a systematic method for developing nuclear power equipment value chain manufacturing risk assessment.

The invention provides a multi-dimensional data fusion-based aging-suitable service coordination method and system for a double-aged community, and the method comprises the steps: collecting multi-source heterogeneous data through an Internet of Things terminal and a community database API interface, constructing a four-dimensional data model of technology, space, service and system, and carrying out the classification and structuring of the data; subjective data are processed by adopting a fuzzy language evaluation method, and objective weighting is carried out on model indexes in combination with an entropy weight method; calculating a comprehensive coordination degree value of the service system by utilizing the coupling coordination degree model; and when the coordination degree is lower than a preset threshold value, generating and outputting a targeted optimization path based on a multi-objective optimization algorithm, including technology upgrading, space transformation, service scheduling and system optimization. The system comprises a data acquisition module, a coordination degree evaluation module, a dynamic optimization module and a user interaction module. According to the method, the problem of resource mismatching caused by data splitting and assessment missing of an existing intelligent old-age care system is solved, and accurate, efficient and fair configuration of old-age care services is realized.

The invention provides an electric vehicle fire tracing method, system and device and a medium. The method comprises the steps that multiple fire features and fire reasons of an electric vehicle are obtained, the fire features are classified, multiple state categories are obtained, the fire features form a state space, and the fire reasons form an action space; determining the membership degree of each fire feature on a fuzzy linguistic variable value threshold by adopting a trapezoidal membership degree function; setting a state transition constraint according to the state category, and then iteratively learning a Q value of any action in any state execution action space in the state space by using a Q learning algorithm based on the state transition constraint and the membership to obtain a plurality of related Q values; and selecting the fire reason corresponding to the maximum correlation Q value as the fire reason of the current electric vehicle. The problems that in the prior art, fire source tracing related data are missing, judgment depends on expert experience, objectivity is difficult to guarantee, and rapid positioning cannot be achieved are solved.

The invention provides a phosphine production equipment control method and device, equipment and a medium, and belongs to the technical field of automatic control, and the method comprises the steps: mapping a real-time operation parameter into a corresponding fuzzy linguistic variable based on a preset membership function; based on the fuzzy linguistic variable of the refining unit, determining a target adjusting unit according to a preset top fuzzy rule; determining a first adjustment instruction corresponding to the target adjustment unit according to a preset middle-layer fuzzy rule based on the target adjustment unit and the fuzzy linguistic variable of each production equipment unit; based on the target adjustment unit, the first adjustment instruction and the fuzzy linguistic variable of the reaction unit, determining a second adjustment instruction of the reaction unit according to a preset bottom fuzzy rule; and issuing the first adjustment instruction and the second adjustment instruction to the corresponding production equipment units so as to realize control of each production equipment unit. According to the phosphine production equipment control method and device, the equipment and the medium provided by the invention, the equipment adjustment accuracy can be improved.

The application relates to a semantic asymmetric similarity recommendation system considering user preference consistency, and belongs to the technical field of recommendation. The application comprises the following steps: acquiring and cleaning data information; converting scores into fuzzy language terms; acquiring a user set U that has scored on a target item i i ; calculating semantic similarity between items by means of a probability language term set theory; acquiring preference information of users on items i and j; calculating user preference consistency between items by means of a Bhattacharyya coefficient method; adjusting semantic similarity by using the user consistency result; acquiring the number of common evaluation items of items i and j and the number of user evaluations of the target item i, and calculating the asymmetric relationship between items by means of a Sigmoid function; breaking the symmetry of weighted semantic similarity by means of the asymmetric relationship between items; calculating a predicted value of a target user u on an un-scored item by means of a score prediction method; sorting a prediction set, and pushing the first n items with the highest predicted values to the target user u.

The present invention discloses a method for intelligently coupling pressure-flow-deformation control of spiral anchor foundation grouting, which relates to the technical field of foundation grouting technology, including: matching a preset engineering parameter set according to the specification parameters of the spiral anchor and the type of soil in which it is located; collecting grouting data of each grouting channel, and calculating grouting deviation data in combination with the engineering parameter set; fuzzifying the grouting deviation data and converting it into fuzzy language variables; inputting the fuzzy language variables into a preset fuzzy rule library for reasoning, and outputting PID parameter corrections; dynamically adjusting the parameters of the PID controller according to the corrections to generate a pump speed adjustment instruction; executing the pump speed adjustment instruction and collecting the grouting data after execution; obtaining the soil permeability coefficient by inversion through the construction of a digital twin model, and optimizing and updating the fuzzy rule library in combination with the grouting data after execution. This application is used to solve the problem that the traditional spiral anchor foundation grouting process has poor adaptability to complex geology.

The invention discloses an artificial intelligence-based policy text key content extraction and analysis method. The method comprises the following steps of: establishing a structured keyword knowledge base, identifying and explaining a retrieval intention by adopting a large model, acquiring literature contents, and classifying and labeling the literature contents to obtain a labeling result; evaluating the labeling result by using the large model to obtain an evaluation result; aggregation processing is carried out on policy content in a time period in the labeling result, a vocabulary structure map and an evolution trend are generated, and an analysis result is obtained; and according to the analysis result and the evaluation result, in combination with the policy orientation demand input by the user, generating a policy suggestion text conforming to the document specification. The mandatory and suggestion of terms are accurately judged, and the problem that an existing model is insufficient in fuzzy language processing is avoided. In industry discrimination, an action verb and industry behavior matrix mapping mechanism is introduced, and the directivity and exclusiveness of industry tags are improved in combination with subject co-occurrence features.

This invention discloses a fuzzy multi-attribute decision-making evaluation method and system. The method includes defining a hesitant fuzzy language terminology set; determining the evaluation object and its influencing factors based on the hesitant fuzzy language terminology set to form a factor set, and assigning weights to each influencing factor to determine the membership function of each factor; performing fuzzy synthesis operations on the membership function of each factor and its corresponding weights to obtain a comprehensive membership value; and performing fuzzy evaluation on the evaluation object based on the comprehensive membership value to obtain a fuzzy comprehensive evaluation result of the evaluation object. This invention's multi-attribute decision-making method, capable of handling incomplete and imprecise fuzzy information, plays a crucial role in ensuring the rationality and accuracy of investment risk assessment.

The invention discloses a slope safety level classification method based on a fuzzy language neighborhood grain concept, and relates to the technical field of slope safety, and the method comprises the steps: collecting slope sample data, detecting slope condition features, and constructing a language concept set of the slope condition features by using language terms, constructing a binary relationship between the slope condition features and the language concept set, determining a neighborhood of a slope sample through cosine similarity, and generating an initial fuzzy language neighborhood grain concept space; on the basis of the initial fuzzy language neighborhood grain concept space, the fusible concept clusters in the subspaces are marked, and a fusion concept space is generated through weighted fusion; and based on the fusion concept space, carrying out slope safety classification on the new slope sample through the minimum identification degree. Therefore, the slope safety level classification method based on the fuzzy language neighborhood grain concept is suitable for slope safety level classification of complex slopes, and reference is provided for flexible classification and multi-factor coupling influence quantification of special slopes.

The invention discloses an intelligent supplier selection method and system, and belongs to the technical field of enterprise resource management and decision support. The system comprises a supplier resource library module used for storing and managing data of suppliers; the supplier admission preliminary screening module is used for aggregating qualitative evaluation of a plurality of decision-making experts based on a possibility distribution hesitation fuzzy language set model, and processing data of suppliers according to a preset comprehensive evaluation value threshold value to obtain potential suppliers; the evaluation index system management module dynamically configures a differentiated performance evaluation index system comprising three dimensions of economy, society and environment for different types of suppliers in the supplier resource library module; the comprehensive evaluation engine module is constructed based on an intuitionistic fuzzy set theory; and the supplier portrait module is used for visually displaying the comprehensive information and the evaluation result of the supplier. According to the method, the defects of high subjectivity, single index and insufficient fuzzy information processing capability in the existing supplier evaluation method are overcome.