34 results about "Risk adjustment" patented technology

The invention discloses an automatic driving safety-efficiency decision-making method based on risk soft constraint, and belongs to the technical field of automatic driving decision-making. The problems that a traditional automatic driving decision-making method is poor in extreme scene adaptability and lagged in risk response in the prior art are solved. According to the method, an automatic driving safety-efficiency decision-making framework is constructed, the environment state of an environment perception layer is input into a multi-expert strategy layer, three experts are adopted to set the multi-expert strategy layer, and candidate car-following actions are output through the multi-expert strategy layer; embedding the risk adjustment mechanism into a loss function of each expert in a multi-expert strategy layer to obtain an Actor network loss function of each expert; on the basis of the output candidate car-following actions, taking a basic reward function as a basic behavior constraint of all experts; and generating an automatic driving safety-efficiency decision. The method effectively improves the interpretability of the automatic driving decision-making method and the robustness of the car-following strategy, and can be applied to automatic driving decision-making.

The invention discloses a homomorphic encryption-based cross-industry health insurance data sharing and privacy protection method, and relates to the technical field of health insurance data security, and the method specifically comprises the steps: standardizing medical and insurance industry core data, quantifying key indexes such as a disease clinical risk value and an occupational basic risk coefficient, achieving the format unification of cross-industry data, and achieving the privacy protection of the cross-industry data; further generating ownership, risk and business labels, carrying out encryption processing on data through homomorphic encryption on the risk labels based on three scenes of data sensitivity and business influence grading, business label binding pricing, underwriting and claim settlement prediction, adding an integrity check code to high-risk data, screening ciphertexts based on the labels, and then executing fusion calculation; the comprehensive risk adjustment coefficient ciphertext is generated, the data integrity is verified, the comprehensive risk adjustment coefficient is obtained after collaborative decryption, the comprehensive risk adjustment coefficient is applied to premium pricing, underwriting conclusion generation and claim risk pre-judgment, and the scientificity and accuracy of health insurance pricing and underwriting decision making are improved.

The invention discloses a coal cutter cutting interference prevention method and system based on point cloud and infrared images. The method comprises the steps that a radar sensing module and an infrared sensing module are installed; synchronously acquiring three-dimensional point cloud data and infrared image data of the target monitoring area; the three-dimensional point cloud data and the infrared image data are preprocessed, aligned in the time dimension and registered in a space coordinate system; performing feature extraction on the three-dimensional point cloud data and the infrared image data, performing feature fusion, and extracting space attitude parameters of the face guard; carrying out risk grade discrimination, and marking an interference position; and generating a risk avoiding control instruction according to the risk level, and executing a risk avoiding adjustment action. According to the system, a processing module comprises a data preprocessing module, a multi-modal information fusion module, an identification module and a decision control module, and the processing module is connected with a radar sensing module and an infrared sensing module. According to the invention, accurate monitoring and active prevention of the cutting interference state of the side protection plate and the coal mining machine roller can be realized.

The invention relates to a multi-factor dynamic correction investment benefit intelligent evaluation system, in particular to the field of investment evaluation, and aims to capture macroscopic event and project risk index impact in real time and dynamically generate factor impact coefficients through an event-driven factor correction module, so that the response speed and sensitivity of a model to project sudden change are remarkably improved, and the evaluation efficiency is improved. The self-adaptive weight optimization module utilizes a deep reinforcement learning framework to continuously optimize factor weight distribution based on revenue after risk adjustment in a rolling time window so as to realize self-adaptive adjustment of an investment strategy and optimization of a revenue-risk ratio, and the abnormal conduction early warning module constructs a dynamic directed graph and combines a graph neural network technology to realize early warning of the abnormal conduction. According to the method, abnormal factor conduction paths can be perspectively recognized, systematic engineering risks can be effectively warned, a strategy execution module fuses weight optimization results and risk warning signals, rebalance is executed under the condition that investment cost and risk control constraints are strictly met, and finally a project configuration scheme giving consideration to revenue, robustness and real-time performance is generated.

The invention relates to a method and a system for adjusting an airline operation strategy according to a civil aviation airline dynamic risk. The method comprises the following steps: calculating an abnormal confidence coefficient score according to an airline throughput; calculating a throughput deviation rate according to the route throughput and a preset throughput; calculating an environment risk factor according to the weather information and the season information; calculating a final risk value according to the abnormal confidence score, the throughput deviation rate and the environmental risk factor; adjusting a route operation strategy according to the final risk value; according to the method, the final risk value is calculated through factors such as the air line throughput, the weather information and the season information, automatic risk calculation can be realized, the air line operation risk can be obtained in time by considering various risk influence factors, and the risk early warning efficiency is improved; and an airline operation strategy is adjusted according to the final risk value, so that the airline operation loss is reduced, reference can be provided for aviation finance, and the investment risk of aviation finance is reduced.

A risk-sensitive code generation computing system receives query data indicating a requested code section. A code attribute evaluation module determines attributes that indicate characteristics of the query data or the requested code section. Based on the attributes, the code attribute evaluation module calculates risk level data for the requested code section. A code generation module selects, based on the risk level data, a set of training resources. Based on the selected training resources, the risk-sensitive code generation computing system modifies training of a trained neural network model. The modified trained neural network model generates a risk-sensitive code data object based on the requested code section and the risk level data. The risk-sensitive code generation computing system provides at least a portion of the risk-sensitive code data object to an additional computing system.

This invention discloses an artificial intelligence-based dynamic credit risk assessment method. This method continuously integrates multi-source real-time data streams with static historical data, utilizes a deep reinforcement learning-trained agent to generate dynamic risk adjustment factors, and employs an attention mechanism to non-linearly couple these factors with a basic credit score. The final output is a real-time dynamic credit score and an interpretable credit decision. By constructing a closed-loop system from real-time perception and dynamic assessment to interpretable output, this invention achieves minute-level continuous monitoring and proactive early warning of borrower credit risk. This solves the problem of delayed risk capture caused by the static nature of data and models in traditional methods, significantly improving the timeliness, accuracy, and automation of risk management.

The present application relates to the technical field of informationization of oil exploration and development and digital processing of whole life cycle management of industrial assets, in particular to a whole life cycle operation and maintenance management system for an oil downhole transmitter, comprising: an asset data management module for building a whole life cycle data lake serving asset value analysis; a benchmark valuation modeling module for generating a theoretical asset value curve of the transmitter under the assumption of no environmental stress; a risk quantification correction module for outputting a risk-adjusted theoretical residual value; a management performance analysis module for calculating a management performance residual after stripping the influence of environmental risks; a decision and execution module for automatically generating differentiated management instructions for asset disposal, inventory strategy adjustment or supplier evaluation, and driving downstream enterprise resource planning systems or inventory control systems to perform closed-loop operations; the present application effectively solves the phenomenon of shirking operation and maintenance responsibilities due to poor well conditions.

The present application relates to the technical field of artificial intelligence, and especially relates to a multi-agent cooperation ability improving method based on agent self-supervised learning, which comprises the following steps: for each iteration of the Monte Carlo tree search self-refining algorithm, determining a parent node selected in each iteration in a search tree as a target parent node, obtaining a total number of historical visits of the target parent node and a child node value set of the target parent node; obtaining a benchmark value according to the total number of historical visits; constructing a risk adjustment compensation item of the target parent node according to the overall value change of the child node value set; optimizing and adjusting the benchmark value by using the risk adjustment compensation item to obtain a final updated value of the target parent node, updating the search tree by using the final updated value of the target parent node until a preset iteration condition is met to obtain a target search tree, and performing multi-agent cooperation according to the target search tree, which significantly improves the ability of multi-agent cooperation by using the Monte Carlo tree search self-refining algorithm.

The invention relates to the technical field of unmanned aerial vehicles, in particular to a multi-unmanned aerial vehicle cooperative investigation scheduling method based on real-time parameter judgment, and the method comprises the steps: dividing sub-regions; constructing a path; collecting historical data; calculating energy consumption; evaluating the risk; adjusting the task; and correcting the threshold value. According to the method, the to-be-surveyed area is scientifically divided into a plurality of controlled sub-areas by integrating geographic information, obstacle distribution, an electromagnetic environment and task requirements, and an optimized flight path and a task topological structure are constructed on the basis; dynamic monitoring and calculation of parameters such as energy consumption, residual electric quantity, task priority, obstacle proximity, height deviation and electromagnetic interference in the flight process of the unmanned aerial vehicle are realized, and a flight risk index is effectively generated. The problems of low task efficiency and limited flight safety caused by fixed path planning, insufficient energy consumption and risk assessment and environmental interference are effectively solved.

The invention relates to the technical field of medical instruments, in particular to a track monitoring force feedback obstetric forceps method and system, and the method comprises the following steps: obtaining three-axis force and track coordinates, matching to generate a traction included angle sequence, extracting an included angle trend, recognizing an offset risk, adjusting a track node direction, analyzing a pressure distribution change trend, and positioning an abnormal stress region. And generating an attitude offset early warning signal. According to the method, the three-axis stress information and the tong head track space coordinates are fused and matched, accurate correlation between the traction angle and the path change can be achieved, the space offset risk is identified by combining the change trend of the included angle, the change direction of the traction track section is compared by utilizing the direction vector trend of the continuous time period, and the traction accuracy is improved. The traction direction and track consistency improvement is guided through path node fitting operation, the pressure intensity concentration trend position is recognized in combination with pressure intensity data distribution, the recognition capacity for clamping deviation and a risk contact area is improved, and real-time recognition, dynamic adjustment and risk prevention and control of the operation process are achieved.

The application relates to the field of financial risk assessment, and specifically discloses a user financial risk intelligent assessment method and system, which comprises the following steps: constructing a three-dimensional big data security protection framework to control user multi-type and multi-modal data in all links; constructing a collaborative framework based on a federal learning hybrid architecture, intelligently analyzing data by adjusting an AI model cluster, a workflow engine and a financial large language model after adjustment through a reinforcement learning intelligent agent; constructing a three-dimensional portrait model, extracting special features of digital financial scenes such as internet loans, dynamically updating and outputting scene-based risk positioning results, and realizing accurate portrait; calculating a dynamic accurate pricing formula based on a formula dynamic interest rate pricing = benchmark interest rate * risk adjustment coefficient * scene adaptation coefficient * market fluctuation coefficient, optimizing coefficient weights through an intelligent agent, and realizing dynamic accurate pricing; and outputting three-layer interfaces of a regulatory level, a financial institution business level and a user level. The application provides a standardized and efficient technical solution for user financial risk intelligent assessment.

The present invention relates to a method and apparatus for evaluating the technical value of research and development technologies, which enables fair evaluation of technical value by appropriately applying risk factors associated with technology research and development activities. The method for evaluating the technical value of research and development technologies according to the present invention is provided to enable fair evaluation of research and development technologies by first calculating the net present value of total sales (a) from the first year to the expected product life cycle period (n), the risk-adjusted net present value of research and development expenses (b) from the first year to the research and development completion year (k), the costs required to generate sales after the research and development activities from the research and development completion year (k+1) to the expected product life cycle period (n) (c), and the residual value (d) after the end of the product life cycle (PLC).

This reinforcement learning device learns a policy for determining the next action of an agent on the basis of an environmental state and a reward earned by the agent for the action thereof, the reinforcement learning device comprising: an estimation unit that uses, as an initial model, a base model which estimates an expected value of a reward and which does not take risk into consideration, to sequentially estimate a risk-corrected reward, which is a reward that takes risk into consideration; and a learning unit that sequentially learns an agent policy on the basis of the risk-corrected reward.

The invention mainly relates to the technical field of semantic recognition, and provides a semantic risk assessment and restoration method based on a multi-modal semantic fingerprint in order to carry out real-time dynamic monitoring and verification on a prompt injection attack semantic intention, the core of the method is that the multi-modal semantic fingerprint is acquired based on a text input by a user, and the semantic risk assessment and restoration method is applied to the text judged to be semantic anomaly. Constructing a semantic change track based on the multi-text modal features of the text and the historical text modal features, and calculating the semantic drift degree of the current text relative to the historical text based on the semantic change track; performing intention consistency verification, and calculating an intention consistency score; obtaining a long-term semantic behavior difference between the current semantic text and the user based on the multi-modal semantic fingerprint of the current text; and calculating the semantic risk of the current text based on the semantic drift degree, the consistency score and the semantic behavior difference, and outputting or repairing the texts of different risk levels according to a formulated repairing strategy to realize real-time risk adjustment for different users under different contexts.

This application relates to the field of advertising delivery technology, and more particularly to an advertising delivery decision generation method and system based on neural time-series point processes. The method includes acquiring historical user interaction data and converting it into a continuous event sequence, while simultaneously calculating the time interval between adjacent events; calculating the user's continuous time state using a state encoder based on the continuous event sequence and time intervals; constructing a quantile regression value evaluation network to perform quantile evaluation on the long-term cumulative reward distribution of candidate actions in the continuous time state to obtain a quantile representation of the value distribution; calculating cognitive uncertainty based on the quantile representation and constructing an enhanced reward to adjust the reward items in the evaluation network training; calculating the risk-adjusted value of candidate actions using the quantile representation and combined with preset risk preference parameters; determining the target candidate action according to the principle of maximizing the risk-adjusted value and generating the corresponding advertising delivery decision. This application enables the accurate determination of advertising delivery strategies.

The invention relates to the field of supply chain management, and particularly discloses a material delivery dynamic residual buffer time judgment method and system, a terminal and a medium, and the method comprises the steps: obtaining the initial plan buffer time of an order; calculating the accumulated consumed buffer time based on the deviation between the actual progress and the planned progress of the order in each link of the supply chain; based on the real-time internal and external risk data, obtaining a dynamic risk adjustment amount through a rule engine or a pre-trained risk adjustment amount prediction model; and calculating the current dynamic residual buffer time according to the initial plan buffer time, the accumulated consumed buffer time and the dynamic risk adjustment amount. The authenticity and timeliness of time judgment are improved, and the reliability and efficiency of material delivery are improved.

The invention relates to the technical field of power distribution area inverter cooperative control, and discloses a distributed cooperative control method, system and device for a power distribution area and a medium, and the method comprises the steps: calculating the real-time risk values of a plurality of risk indexes corresponding to the multi-dimensional operation data of the power distribution area; a risk adjustment mechanism based on operation scene features is introduced for correction, and a comprehensive risk index and a dominant risk type of the power distribution area are obtained; when the comprehensive risk index exceeds a preset high-risk threshold value, controlling each inverter node in the power distribution area to exchange state information so as to determine a master node and a plurality of slave nodes through a distributed election algorithm; then, the master node is controlled to calculate a total adjustment demand according to the dominant risk type, and an optimal resource allocation scheme is solved and issued to the corresponding slave nodes in combination with the maximum safety adjustment amount and the expected contribution degree received from the slave nodes so as to control execution of the slave nodes; quick response to real-time risks is realized, and the distributed cooperative control efficiency is improved.

This invention relates to the field of data processing, and more specifically, to a dynamic task scheduling method and system for AI agents using multi-model collaborative reasoning. The method includes: collecting historical data from computing nodes; statistically analyzing the mean, standard deviation, and covariance of task duration and queue length; calculating a risk adjustment factor based on the covariance and determining a directional switch; penalizing and adjusting the mean duration based on both factors to obtain the risk perception prediction duration; constructing a directed acyclic graph (DAG) of task dependencies; calculating the directed path inertia based on the signal-to-noise ratio of each node; and obtaining the scheduling priority by combining the dynamic upward rank and a suppression factor; and selecting the computing node that minimizes the earliest dynamic completion time for each task according to priority. This invention suppresses short-term scheduling oscillations by distinguishing between real congestion and random noise, and improves the stability of system throughput and task completion time by stabilizing critical path identification through directed path inertia.

The embodiment of the invention provides a case allocation method based on dynamic priority and a related device, and relates to the technical field of computers. The method comprises the following steps: adjusting the number of cases allowed to enter the system in unit time according to the current allowed rate of the system; the index value of each to-be-audited case entering the system under each evaluation dimension is obtained, the dynamic weight of each evaluation dimension is obtained, and the dynamic weight of each evaluation dimension is dynamically updated through reinforcement learning with maximized revenue and processing efficiency after risk adjustment as target functions; and calculating a priority score of each to-be-audited case based on the dynamic weight of each evaluation dimension and each index value of each to-be-audited case, and allocating each to-be-audited case according to the priority score of each to-be-audited case. Thus, the fundamental defects that in the prior art, queue management is static, and real-time changes cannot be responded are overcome, the problems of resource waste and risk improvement are avoided, and accurate distribution of cases is achieved.

The invention belongs to the technical field of expressway operation safety management, and discloses a mountain area expressway section traffic risk assessment method considering discrete risk sources, comprising the following steps: S1, identifying all discrete risk structure points included in a to-be-assessed section, and obtaining traffic risk values of the structure points; s2, identifying whether a road section risk source exists in the target road section, and calculating a traffic risk value of the road section risk source; s3, aggregating the structural points and the risk value of the road section risk source into a basic risk of the road section; s4, acquiring traffic flow and meteorological early warning data of the target road section, and calculating a dynamic risk adjustment coefficient of the traffic flow and meteorological early warning data; s5, acquiring historical traffic accident data and road attributes, and determining an additional risk correction coefficient; and S6, calculating the traffic risk. According to the method, the traffic risk condition of the highway in the mountainous area can be reflected from the local to the whole comprehensively, the interaction effect among the factors is described accurately, and accurate support is provided for operation safety management and control of the highway in the mountainous area.

The application provides a risk adjustment item determination method and device, electronic equipment and a storage medium. The method comprises the following steps: obtaining a historical fixed value of a historical month uploaded in advance; determining an i-th statistical month and an i-1-th statistical month corresponding to the i-th statistical month; if the i-1-th statistical month belongs to the historical month, determining an i-th risk adjustment item of the i-th statistical month based on an i-th estimated risk cost cumulative value of the i-th statistical month and the historical fixed value; if the i-1-th statistical month does not belong to the historical month, determining an i-1-year risk version adopted by the i-1-th statistical month based on a current statistical time of the i-th statistical month; determining an i-1-th estimated risk cost of the i-1-th statistical month based on the i-1-year risk version; and determining the i-th risk adjustment item of the i-th statistical month based on the i-th estimated risk cost cumulative value, the i-1-th estimated risk cost and an i-1-th estimated risk cost cumulative value. The method can improve the determination accuracy of the risk adjustment item.

The application relates to the technical field of pipeline monitoring, and discloses a pipeline risk monitoring system and method. The system comprises a collection module and a processing module; the collection module determines a collection operation mode of a monitoring point based on a temperature influence coefficient; the processing module is configured to establish a time-parameter function based on parameters collected by a plurality of operation parameter sensors at the same time according to the collection operation mode, determine a risk level of the monitoring point according to a slope of the time-parameter function and a parameter change length, and determine a risk prediction value of the monitoring point based on a parameter set of each operation parameter sensor in the plurality of operation parameter sensors and a risk evaluation value of the monitoring point according to the risk prediction value and a risk adjustment coefficient; and the processing module is further configured to determine a pipeline risk monitoring result of the monitoring point according to the risk level and the risk evaluation value. The application can obtain a plurality of parameters according to dynamic adjustment of a collection operation mode, and has good monitoring effect.

The invention discloses a cost control strategy recommendation system based on reinforcement learning, and the system comprises a data collection module which is used for collecting historical cost data; the data preprocessing module is used for preprocessing the historical cost data; the dual-channel embedded coding module is used for executing embedded mapping through an improved QTransform network; the layered Q function modeling module is used for constructing a global Q function and a local Q function through an improved QTransform network and generating a fused Q value feature sequence; the risk adjustment attention module is used for constructing a risk adjustment factor and carrying out risk perception modeling on the fused Q value feature sequence; and the cost control strategy generation module is used for obtaining a target cost control strategy vector through a Pareto non-dominated sorting method. And the strategy execution and model updating module is used for executing a cost control action and carrying out offline incremental updating on the improved Q-Transform network. According to the invention, the precision, efficiency and risk adaptability of the cost control strategy are improved.

A stroke recurrence risk assessment and personalized management method and system, the system comprises an application server, the application server comprises a database module, a recurrence risk dynamic prediction model module and a personalized management strategy generation module. The recurrence risk dynamic prediction model module is used to determine a long-term static risk index reflecting the inherent risk of the patient based on the clinical data stored in the database module, determine a short-term dynamic risk adjustment index reflecting the instantaneous risk contribution based on the dynamic feature sequence in the self-management data; by executing a risk coupling algorithm, the long-term static risk index and the short-term dynamic risk adjustment index are fused and calculated by using a weight coefficient to obtain a total risk index; the personalized management strategy generation module is used to convert the total risk index into a query vector, retrieve a matched guideline segment in a stroke management knowledge base; input the guideline segment as a constraint condition into a large language reasoning model to generate a personalized intervention scheme.

This invention belongs to the field of highway safety management and risk assessment technology, and discloses a method for assessing the traffic risk of key infrastructure structural points on mountainous highways. The method includes the following steps: S1. Acquiring multi-source data for the target structural point, including natural disaster data, technical condition data, road alignment data, meteorological data, traffic flow data, and special control measures data; S2. Determining the basic risk value for classification and grading of the structural point based on the natural disaster data and technical condition data through a risk assessment matrix; S3. Calculating the basic risk value of the structural point's alignment characteristics based on the road alignment data; S4. Determining dynamic risk adjustment coefficients based on meteorological data and traffic flow data; S5. Determining additional risk correction coefficients based on special control measures data; S6. Calculating the traffic risk value of the target structural point. This invention achieves quantitative assessment and classification of the traffic risk of structural points, providing a scientific basis for monitoring, early warning, and special rectification of high-risk locations.

The invention discloses an insurance rate adaptive calculation method and system based on a dynamic Bayesian network, and relates to the technical field of insurance rate optimizing.The method comprises the steps that multi-source heterogeneous information is obtained through dynamic collection of a multi-source collection interface, and the dynamic Bayesian network is constructed in combination with a preset network structure; acquiring a real-time risk assessment result through a dynamic Bayesian network, and processing the real-time risk assessment result to obtain a real-time risk vector; evaluating and analyzing the real-time risk vector in combination with a historical risk database to obtain a real-time risk adjustment coefficient; and adjusting the predetermined premium rate to obtain a dynamic premium rate. The technical problems that insurance rate calculation depends on a fixed rule, multi-source information is difficult to fuse and risk changes cannot be responded in real time in the prior art are solved, and the functions of fusing the multi-source information based on the dynamic Bayesian network, evaluating the risk in real time and dynamically adjusting the rate are achieved. And the accuracy and timeliness of the insurance rate optimization are improved.

The invention discloses a credit line adjusting method and device, electronic equipment and a computer program product. Relates to the field of financial science and technology, and comprises the following steps: obtaining product data of a product produced by a target institution, and extracting financial data of M raw materials required for producing the product from the product data, M being a positive integer; the financial data of the product is calculated according to the financial data of the M raw materials, the demand change rate of the product is calculated based on the financial data of the product, and the demand change rate is obtained based on the combination of the sub-demand change rates of the M raw materials; and determining a risk adjustment strategy of the target institution based on the demand change rate of the product, and adjusting the credit line of the target institution according to the risk adjustment strategy. According to the method and the device, the technical problem of low adjustment accuracy when the credit line of the target mechanism is adjusted in the prior art is solved.

This invention specifically relates to a risk assessment method for hydrological-power coupled systems under rainstorm disasters, belonging to the technical field of distribution network system risk assessment. By establishing a four-dimensional assessment system encompassing hazard, exposure, vulnerability, and adaptability, this invention not only quantifies the direct damage of hydrological disasters to the power system but also innovatively defines secondary power hazards, characterizing the disaster amplification feedback loop of "power failure → drainage failure → exacerbated flooding → further damage to power facilities" at the mechanistic level. This invention introduces adaptability as a risk adjustment factor, comprehensively calculating the adaptability coefficient through indicators such as infrastructure density, road density, and the proportion of educated population. It scientifically demonstrates that improving regional adaptability and resilience can directly reduce overall risk, indicating a strategic transformation path from simply mitigating disasters to enhancing system resilience.

The invention relates to the technical field of chinlon yarn manufacturing, and discloses a chinlon slice melting and mixing parameter feedback control method and system.The method comprises the steps that technological parameter sequences such as the temperature of each temperature zone of a machine barrel, the rotating speed of a screw and torque are collected in real time; constructing a heat-shear historical state quantity reflecting a melt heat-shear cumulative effect on the basis of the sequence; comparing the state quantity with a reference state quantity, and judging the historical equivalence of the melt; then combining the state quantity and an equivalence result, and dividing the working condition into a reversible adjustment state, a critical risk state or an irreversible damage state; and finally, selecting a compensatory adjustment, low-risk adjustment or emergency control strategy according to the judgment state, and outputting a corresponding control instruction. According to the method, the hidden historical difference and the reversibility interval of the melt can be accurately identified, quality damage caused by blind parameter adjustment is avoided, and the production stability and the yield are improved.