255 results about "Expert evaluation" patented technology

The invention discloses a geological disaster prediction system which comprises a data acquisition module, a geological environment space information monitoring module, a monitoring center, a predictive analysis module, an expert assessment module, a mathematic model building module, a holographic laser projection system, a virtual parameter actuation module, a virtual sensor and a simulation analysis module. Real-time and comprehensive monitoring of the geological environment is achieved, the geological condition can be shown in front of a worker through the holographic laser projection system, the worker can observe the geological changing condition personally on the scene, and reliable references are provided for treatment measure formulation; on the basis of Flac 3D numerical simulation, models corresponding to different monitoring data are calculated, the prediction analysis precision is improved, the obtained treatment measures can be subjected to simulation analysis, and therefore the specific treatment measures can be obtained; the ZigBee network topological structure is adopted, and therefore the multi-node and large-area monitoring requirement is met.

The invention discloses an intelligent tunnel construction security monitoring system comprising a deformation monitoring sensor group, a video data collecting module, an environment monitoring sensor group, a monitoring point internal stress collecting module, a data processing module, a central processing unit, a prediction analysis module, an expert evaluation module, a dangerous action judgment module, a mathematical model building module, a virtual actuator, a virtual sensor and a man-machine operation module. According to the intelligent tunnel construction security monitoring system, omni-directional real-time detecting on a tunnel construction situation is achieved so as to obtain various evaluation results of the tunnel construction situation, detecting results are high in accuracy, additionally, by building a tunnel construction mathematical model, prediction and simulative analysis of the follow-up situation of tunnel construction are conducted, problems in the tunnel construction process can be discovered timely, and a reasonable selection of tunnel construction schemes is achieved; and the intelligent tunnel construction security monitoring system has the function of automatic evaluation of dangerous actions and dangerous environments, and construction safety of construction personnel is further guaranteed.

The present invention belongs to voice field of technology, pronunciation quality evaluation method of computer Computer Aided Language Learning system includes: calculation of the matching fraction, calculation of the sensing fraction based on Mel frequency scale, calculation of the segment length fraction and calculation of the keynote fraction, and processing fusion after mapping the above fractions; the pronunciation quality evaluation method of the invention has better robustness, high pertinency with the expert evaluation, used for interactive language learn and automatic spoken language test.

The invention discloses an intelligent piano teaching system, which comprises a sound acquisition module, a video acquisition module, a man-machine interaction module, a sound processing module, a pressure sensor, a pitch extractor, a beat extractor, a music theory information decoder, a music score generator, a video data processing module, an action standard judgment module, an action guidance suggestion output module, a three-dimensional teaching module, an expert evaluation module, a daily task receiving module, a daily task completion condition summarization module, a difficult problem summarization module, a difficult problem answer module, a teacher terminal, a student terminal and a central processing unit. The intelligent piano teaching system improves the intonation degree of piano training; teaching video and training video are released by adopting a dynamic three-dimensional mode, the learning interest and the learning efficiency of students are greatly improved, acquisition and evaluation for learning conditions of each student in the whole teaching process are realized, the playing work of a certain student can be explained selectively, and the intelligent degree is high.

An apparatus and methodological framework are provided, named perfusion angiography, for the quantitative analysis and visualization of blood flow parameters from DSA images. The parameters, including cerebral blood flow (CBF) and cerebral blood volume (CBV), mean transit time (MTT), time-to-peak (TTP), and T_max, are computed using a bolus tracking method based on the deconvolution of time-density curves on a pixel-by-pixel basis. Individual contrast concentration curves of overlapping vessels can be delineated with multivariate Gamma fitting. The extracted parameters are each transformed into parametric maps of the target that can be color coded with different colors to represent parameter values within a particular set range. Side by side parametric maps with corresponding DSA images allow expert evaluation and condition diagnosis.

The invention discloses a civil engineering foundation pit construction monitoring system and monitoring method. The monitoring system comprises a man-machine operation module, a data acquisition module, a video data acquisition module, a central processing unit, a prediction analysis module, an expert evaluation module, a physical model building module, a virtual actuator, a virtual sensor, a simulation analysis module and an alarm modules. The system is safe, practical, convenient, real-time and effective, avoids safety problems in foundation pit construction monitoring, can be used in various construction environment sites to eliminate safety information hidden dangers in a construction process, can effectively detect and manage the construction site, and maintains the normal operation of a detection system of the construction site.

An investment and financing risk assessment method includes the following steps of step 1, collecting information of a user who applies for investment and financing; step 2, utilizing a risk assessment system to analyze the information of the user who applies for investment and financing and obtaining a preliminary analysis result; step 3, distributing the information to an expert evaluation system according to the preliminary analysis result and proceeding to an expert review to obtain an expert analysis result; step 4, generating a risk assessment report according to the expert analysis result and grading the user who applies for investment and financing to a plurality of grades; and step 5, subjecting the user who meets grade requirements to investment and financing information matching according to the risk assessment report. The investment and financing risk assessment method has the advantages of achieving the further processing of the investment and financing information, encoding the information in a standardization mode, quantifying the critical data such as the integrity risk, subjecting the investment and financing information to the intelligent matchmaking trading through the establishment of certain mathematical models, improving the efficiency of the investment and financing transaction greatly, and reducing the cost of the investment and financing transaction.

The invention discloses a karst tunnel water outburst and mud outburst overall process gradual dynamic risk assessment method. The method includes the steps that 1, in the tunnel investigation stage, the tunnel address and the hydrogeological information of the surrounding rock near the tunnel are obtained, that is, the hidden danger environment for water outburst of the tunnel is obtained, and the risk states of the geological conditions of all segments of the tunnel are known; 2, the risk rating value is worked out according to an expert evaluation vector and a factor weight vector, and consistency check is conducted; 3, danger factors are introduced to influence factors of risk evaluation, the hidden danger environment and the danger factors are considered comprehensively, water outburst risk evaluation is conducted, and the segment distribution feature with the tunnel water outburst risk is divided; 4. The values of all indexes are corrected in real time in combination with actual field construction so as to achieve dynamic evaluation of the water outburst and mud outburst risks. The purposes of optimizing construction organization design and avoiding medium and large water outburst geological disasters are achieved through dynamic construction risk evaluation and control, and important data are provided for later-period tunnel operation risks, and the method has very wide application prospects.

The invention discloses a geographic information data acquisition and display system, including a geographic information acquisition module, a man-machine operation module, a video data acquisition module, a data processing module, an expert evaluation module, a graphics rendering module, a regression calculating module, a prediction analyzing module, a central processor, a database file name automatic generation module, a 360-degree phantom imaging module, a simulation analyzing module, a virtual sensor, a transfer node module and a display. The simulation analyzing module repeatedly executes a simulation analyzing algorithm or a simulation analyzing method and transmits the feedback results to the virtual sensor. The virtual sensor receives the feedback results and automatically displays the data. According to the invention, a Beidou module is adopted to achieve data transmission through short messages, which greatly reduces the cost, ensures the real-time transmission of data, reduces the workload of the workers while achieving the 3D simulation of geographic information and comprehensive simulation and analysis of 3D three-dimensional geographic module so as to provides the reliable basis for corresponding measures.

The invention discloses a groundwater pollution detection evaluation system including a sensor group, a positioning module, a camera module, a monitoring and evaluation center, a transfer node module, a physical model building module, a virtual actuator, a virtual sensor, a simulation analysis module, a water quality state evaluation module, an expert evaluation module, a manual expert module, a display screen and a man-machine operation module. Through a Beidou short message communication technology, data transmission is carried out, a communication line is not needed to be erected, use is convenient, all-around real-time detection of groundwater can be achieved, and thus a plurality of evaluation results are obtained and the accuracy of the detection results is high; moreover, through building the physical model, prediction and simulation analysis are carried out for follow-up situation of the water quality, all kinds of water quality treatment schemes are converted into parameters and then act on the physical model, and the reasonable choice of a water quality treatment scheme is achieved.

The invention discloses a fuzzy multi-attribute evaluation-based satellite power supply health degree calculation method. The method realizes the health state evaluation after the failure occurrence of a satellite power supply. According to the method, firstly, an evaluation index attribute set and a reasonable evaluation set are established based on the failure analysis result of a satellite power supply failure mode. Secondly, a fuzzy evaluation matrix is obtained through expert evaluation or other methods. Thirdly, based on the analytic hierarchy process, the initial weight of each evaluation index in the same level is determined. Meanwhile, qualitative attributes are quantified, and then a final comprehensive evaluation result is obtained. In the aspect of health management, results can be divided into 5 levels of health, good, attention, deterioration and disease. In this way, the health degree of an evaluated object can be characterized in the above 5 levels. By adopting the method, the health degree of a satellite power supply during the running process can be calculated in real time. Therefore, the on-orbit safety of the satellite power supply can be improved. Meanwhile, adecision is provided to assist the ground transportation personnel to realize the on-orbit operation management of satellites.

The invention provides a high-rise residential area forced arrangement scheme generation design method based on a conditional generative adversarial network. The method comprises the steps of constructing a high-rise residential area conditional generative adversarial network structure model according to a design task book; Generating a data set under supervised pairing training and calling a Python language to adjust the picture size; Performing alternate iterative training on the network until a Nash equilibrium state is reached, and taking the high-rise residential area contour picture to be planned as an input condition to obtain a high-rise residential area forced arrangement scheme total plane graph; Calling a Python language to obtain a pixel gray scale value of the total plane graph so as to construct a high-rise residential area building geometric model; And establishing a building sunshine, fire-fighting performance and urban skyline combined evaluation system through computer simulation analysis and an expert evaluation method. The high-rise residential area forced drainage design scheme can be supported to make a decision, and meanwhile subjective and objective joint evaluation is carried out on the high-rise residential area forced drainage design scheme through building sunshine, fire-fighting performance and urban skyline analysis.

The invention relates to a high-voltage transmission line icing process integrated prediction method and belongs to the overhead high-voltage transmission line on-line monitoring and early warning technical field. According to the method, icing process historical data of a high-voltage transmission line on-line monitoring system and corresponding micro meteorological data are utilized to establish an icing process fusion prediction system comprising a data pre processing module, an icing process prediction module and a fusion decision-making module. The method includes the following steps that: dimension reduction processing is performed on the meteorological data based on a principal component analysis method, so that the complexity of modeling can be decreased; a multivariable nonlinear regression model, a support vector machine model, an expert evaluation model and a fuzzy reasoning model are utilized to qualitatively or quantitatively predict the icing process of a power transmission line; and a DS evidence fusion theory is utilized to perform united judgment on four prediction results, and an icing early warning level is confirmed. The high-voltage transmission line icing process integrated prediction method has the following advantages that: a modeling process is simplified; the uncertainty of a single model is eliminated, so that the accuracy of prediction is improved; and effective basis can be provided for relevant departments in decision making of icing disasters.

The invention discloses a building construction informationized dynamic monitoring system. The building construction informationized dynamic monitoring system comprises an industrial control computer, a central controller, a digital camera, a deformation monitoring sensor group, a monitoring point internal stress acquisition module, a Beidou module, a prediction and analysis module and a three-dimensional analog simulation analysis module which are mutually connected, wherein the central controller controls the digital camera, the deformation monitoring sensor group and the monitoring point internal stress acquisition module to carry out data acquisition, the acquired data is sent to the prediction and analysis model and the central processor through the Beidou module, and analysis and prediction are carried out on building construction conditions through the prediction and analysis module and an expert evaluation model; a building construction three-dimensional model is built through the three-dimensional analog simulation analysis model, and carrying out three-dimensional analog simulation through a virtual actuator and a virtual sensor which are inserted into the three-dimensional model. The building construction informationized dynamic monitoring system can be applied to various construction environment fields, safety information hidden dangers in the construction process are eliminated, the construction fields are effectively detected and managed, and normal operations of a detection system at the construction fields are maintained.

The invention discloses a remote sensing monitoring and early warning system for an agriculture-forestry ecotone fire disaster, which comprises a man-machine operation module, a video capturing module, an infrared thermal radiation sensor, a satellite video acquisition module, a sensor group, a data processing module, a three-dimensional image constructing module, a central processing unit, a prediction analysis module, an expert evaluation module, a 360-degree illusion imaging module and a warning module. The fiber sensor group is used to cooperate with the satellite video acquisition module and a ground video acquisition module, real-time monitoring on the agriculture-forestry ecotone condition is realized, the system itself is provided with a prediction analysis and early warning function, and the use is convenient; three-dimensional reconstruction on the video data is realized through the three-dimensional constructing model, and observation on the agriculture-forestry ecotone condition by the user is further facilitated; and three-dimensional delivery on the field condition is realized through the360-degree illusion imaging module, a worker can have a reality feeling of being personally on the scene, and making of a fire disaster prevention measure and a fire extinguishing measure is facilitated.

The invention discloses an internet-of-things-based online risk evaluation and control system for an engineering machine. The system comprises a monitoring center, a sale service module, an intelligent expert evaluation analysis knowledge base, an online evaluation module and a global positioning system (GPS) module which is arranged on the engineering machine, wherein the monitoring center, the intelligent expert evaluation analysis knowledge base, the sale service module and the online evaluation module perform data exchange with one another. The system has the advantages of assisting an agent and a financing insurance unit to use an advanced multi-stage locking car and an anti-withdrawal technique to monitor and manage property right vehicles operated outside so as to protect legal economic interests of the agent and the financing insurance unit, assisting a property right unit of a vehicle and a user to know vehicle loan and insurance conditions more conveniently, notifying a client on time and reminding the client in time to guard against financial risks, acquiring and analyzing basic information and maintenance information of the engineering machine, performing online evaluation on the actual value of the engineering machine, and providing expert-level evaluation guidelines to facilitate the online evaluation and sale guidance of vehicles.

The invention discloses an electrical fire monitoring system, comprising a human-machine operating module, a sensor set, a video collection module, a central processing unit, a control command preview module, a prediction analysis module, an expert estimation module, a physical model analog simulation analysis module, a simulation analysis module, and a virtual sensor. The use of multi-mode inputting manner provides great convenience for use; the input of each command is self-provided with authentication information, limiting system control rights is guaranteed, and the input of every control command is traceable; before confirmation of the output of each command, previewing the control command is required, and therefore, output errors of the control command are well avoided and every control command is visualized; real-time monitoring is provided for electrical equipment current and temperature, surroundings and the like, data estimation and analysis functions are self-provided to the system, and the technical problem that electrical fire detection is low in efficiency and poor in detection result is effectively solved; analog simulation analysis can be carried out for late development conditions of electrical equipment according to detected data.

The invention relates to the field of groundwater evaluation. The process of groundwater pollution evaluation is divided into an self-help expert system which can be realized in an online and an expert evaluation system which can be realized in an offline way. According to the online expert system, the groundwater pollution assessment is divided into 8 categories, 35 sub categories and hundreds of subdivision tasks. For each subdivision task, the expert system provides a sample answer and a detailed explanation. After technical representatives of a commissioning party are trained in an unified way, the groundwater pollution preliminary evaluation can be carried out independently on the basis of using online resources. A detailed technical document is generated by the preliminary evaluation, and the prototype of an evaluation report is formed. On the above basis, groundwater assessment experts and the technical representatives of the commissioning party carry out project communication in an online way, a groundwater numerical model is subjected to examination and improvement, and an evaluation report draft is modified and processed. When the evaluation is completed, the ability building and fruit transfer of the commissioning party are completed at the same time.

The invention relates to a bridge hanging basket construction risk assessment method based on a fuzzy analytic hierarchy process. The method comprises the steps that a bridge construction project hanging basket construction safety risk assessment index set is determined; according to expert evaluation opinions, a judgment matrix is obtained through comparison of every two factors, the maximum feature value and weight of the judgment matrix are calculated, and whether consistency of the judgment matrix passes or not is checked; a grade matrix of a single criterion layer is determined by using atrapezoidal membership function, and a primary fuzzy evaluation matrix is obtained via calculation; and finally, a step of comprehensively carrying out secondary fuzzy comprehensive evaluation on themain criterion layer is conducted to obtain a risk evaluation result. The safety condition of the bridge hanging basket construction system is evaluated through the fuzzy hierarchy method, and the method has the advantages of being simple in design, convenient to implement, comprehensive in consideration factor and the like; meanwhile, according to a construction site and a safety system of the construction site, uncertain influence factors causing bridge hanging basket construction accidents can be converted into a model capable of conducting quantitative calculation, and therefore scientific reference is provided for preventing and controlling the hanging basket construction accidents.

The invention discloses an improved Bayesian inverse reinforcement learning method based on combined feedback, and provides an interactive learning method combining expert feedback and demonstration,in an LfF, an expert evaluates the behavior of a learner and gives feedback with different rewards, so as to improve the strategy of the learner. In the LfD, the Agent attempts to learn its policy byobserving expert demonstration. The research algorithm of the method is divided into three learning stages: learning is carried out from non-optimal demonstration; learning from the feedback; demonstration and feedback learning; to reduce states requiring iteration According to the number of actions, the Agent strategy is improved through iteration of the graphical Bayesian rule to enhance the learned reward function, and the speed of finding the optimal action is increased.

The invention discloses a water environment monitoring system, which comprises a sensor group, a video data acquisition module, a panoramic video generating module, a man-machine operation module, a central processor, a water environment evaluation module, an expert evaluation module, a physical model building module, a virtual actuator, a virtual sensor and a simulation analysis module. An underwater robot and a detection device are perfectly combined to realize simultaneous detection on water environment conditions in multiple directions, multiple evaluation results of the water environment conditions are obtained, the detection results are high in accuracy, data transmission is carried out via a Beidou short message communication technology, no communication line needs to be erected, the use is convenient, prediction and simulation analysis on subsequent conditions for the water environment are realized through self definition of the water environment physical model, the virtual sensor and the virtual actuator, various water environment treatment schemes can be converted into parameters to act on the built water environment physical model, and reasonable selection on the water environment treatment schemes can be realized.

The invention discloses a fuzzy TOPSIS evaluation method, which comprises the following steps: 1) obtaining an expert evaluation original matrix and calculating index comprehensive weight; 2) calculating a weight standard decision matrix and positive and negative ideal solutions; and 3) calculating close degree of each candidate evaluation object. The improvement lies in that, in the step 3), a traditional Euler distance formula is improved, preferences of experts for evaluation indexes are considered, and a weight standard Euler distance function is constructed; and the close degree of each candidate evaluation object is calculated by utilizing weight standard Euler distance. The technical effects are that a ranking result obtained under a fuzzy condition has very high robustness; and meanwhile, the problem that when preferences of the experts for evaluation indexes are different, evaluation results are same in an existing TOPSIS evaluation method is prevented.

The invention discloses a forest management system, comprising: a human-machine operation module, a video data acquisition module, a satellite video acquisition module, a satellite visible light monitoring module, a satellite thermal infrared monitoring module, a satellite microwave monitoring module, a forest space information monitoring module used to obtain the forest space information via the fixed high altitude correction points, a data processing module, a dangerous action determining module, a central processor, a predicting and analyzing module, an expert evaluation module, a physical model structuring module, a virtual actuator, a forest area calculating module, a wood category recognizing and statistical module and an alarming module. According to the invention, through the use of the satellite visible light, thermal infrared and the microwave images, it is possible to obtain the forest environment information, the thermal infrared information and the space information; and through the information integration and comprehensive analyzing, low-cost and high-efficient forest monitoring can be realized so as to realize the automatic statistics on the forest area and wood distribution data, therefore, greatly reducing the workload of the working staff.

The invention belongs to the field of shield underneath pass existing tunnel safety risk evaluation, and particularly discloses a shield proximity existing tunnel safety evaluation method based on data mining and data fusion. The method comprises the following steps: establishing a shield underneath pass existing tunnel safety evaluation index system and a risk grading standard; designing a Bayesian network by adopting a fault tree analysis method; obtaining an expert evaluation interval fuzzy set of a root node in the Bayesian network based on a group decision judged by an expert, and fusingthe expert evaluation interval fuzzy set by adopting an improved evidence theory to obtain fuzzy prior probability distribution of the root node of the Bayesian network; and based on the constructed Bayesian network model, carrying out risk probability reasoning and sensitivity analysis of shield underneath passing through the existing tunnel, and determining the safety risk level and key controlfactors of shield underneath passing through the existing tunnel. According to the method, more accurate and reasonable comprehensive evaluation of the safety risk of shield underneath passing throughthe existing tunnel is realized, and a powerful basis is provided for safety risk early warning and control decision of engineering.