45results about How to "Realize intelligent evaluation" patented technology

The invention discloses a system for quantitative management of software defects, which comprises a defect prediction and evaluation module, a process fault diagnosis module and a software defect mending cost estimating module. The defect prediction and evaluation module is used for evaluating and predicting the amount of software defects. The process fault diagnosis module is used for simulating the propagation process of software process faults, expressing fuzzy fault knowledge and providing a target-drive-oriented backward reasoning mechanism and software product fault diagnosis. The software defect mending cost estimating module is used for researching a defect mending cost predicting method so as to calculate mending cost and accurately estimate the defect mending cost. By the system, intelligent evaluation on software defects is realized, efficiency and accuracy in software process fault diagnosis are improved, software process is more controllable, and development process is more highly mature.

The invention provides a receiving-end network voltage stabilization overall process situation assessment and prevention and control method based on responses. The method comprises the steps of S1, obtaining various off-line simulation data or real-time measuring data; S2, constructing equivalent power transmission models of nodes according to node practical transfer power; S3, obtaining a node quiescent voltage stability margin index Vsi of equivalent power transmission model parameters of each node; S4, constructing a node reactive compensation assessment index according to the equivalent power transmission model parameters of each node; S5, setting an early warning threshold value Ncr of the node quiescent voltage stability margin index, and calculating a load shedding estimation of a weaker node when the quiescent voltage stability margin index Vsi of each node is smaller than the Ncr. According to the receiving-end network voltage stabilization overall process situation assessment and prevention and control method based on the responses, a weak node or a weak area in a current operating mode can be found out, a rapid estimation of reactive compensation levels and load shedding of each node is achieved, and the method can be widely applied to the fields of power network planning and online security monitoring.

The invention provides a system and a method for optimizing a cutting process, relating to the technical field of the cutting process. The system comprises an evaluation index selector, a data quantitative processor, a sample classifier, a process scheme evaluator and a process scheme selector. The method for realizing the optimization for the cutting process by adopting the system and on the basis of a particle swarm classifying and self-adaption nerve fuzzy inference system comprises the following steps: generating a training sample set by adopting a particle swarm optimization algorithm according to the collected process index data; establishing a self-adaption nerve fuzzy inference system model by learning the training sample set; autonomously generating a fuzzy inference rule, thereby acquiring an evaluation value and confirming the optimal cutting process scheme. According to the method provided by the invention, the intelligent evaluation and the prior evaluation can be realized; the evaluation process is simple and clear; through the method and the system, different cutting process schemes of a same part can be compared and then the optimal process route can be confirmed; under the condition of guaranteeing the emission reduction and environment protection, the cutting process can be more effectively realized.

The invention relates to the technical field of equipment test identification. The invention discloses a method for constructing an equipment combat test identification index system. The method is anequipment combat test identification index optimization method based on a rough set and a genetic algorithm and comprises the steps that (1) a basic framework of an equipment combat test index systemis constructed; (2) a decision information table is constructed, the concept of the decision information system is derived from a rough set method, and definition is given to the rough set and the decision information system; (3) the attribute reduction method based on the genetic algorithm comprises the following steps: a) chromosome coding, b) fitness function, c) roulette strategy selection operation, d) crossover operation,..; and (4) a simplified index set is obtained to obtain an attribute reduction set of the equipment decision information system. Through the rough set and the genetic algorithm method, various uncertain information can be well processed, qualitative and quantitative information is analyzed and mined, attributes of the information are reduced, and a simplified indexset is obtained; intelligent evaluation is achieved, and the method is simple, visual and good in effect.

The invention discloses a micro-expression recognition-based user risk degree analysis method. The method comprises the following steps of: acquiring a face image of a user in a loan service handlingprocess; Performing micro-expression recognition on the face image to obtain scores of each preset subclass of micro-expressions corresponding to the face image; Determining a target large-class microexpression corresponding to the face image according to the score of each preset small-class micro expression; Calculating a total score value of each preset subclass micro-expression contained in the target subclass micro-expression; And determining the risk degree of the user according to the calculation result. The user risk degree is intelligently evaluated on the basis of micro-expression recognition, so that the problem that the user risk management and control effect is not ideal in the prior art is solved, the analysis efficiency and accuracy of the user risk degree can be improved, and more effective user risk management and control are realized.

The invention discloses an experiment capability intelligent evaluation method based on virtual reality. The method comprises the following steps: S1, setting an assessment link, assessment key pointsof the assessment link and scoring standards corresponding to the assessment key points, wherein the assessment link comprises an experiment article, experiment operation and an experiment result; s2, performing a virtual reality experiment by the user, and recording experiment articles used by the user in the virtual experiment process, the performed experiment operation and the obtained experiment result; s3, according to the set scoring standard corresponding to each assessment key point, respectively carrying out intelligent scoring on the experiment article used by the user in the virtual experiment process, the experiment operation and the obtained experiment result; and S4, obtaining the total score of the user experiment according to the experiment operation carried out by the experiment article and the score result of the experiment result. Experimental ability can be comprehensively investigated, the assessment level is clear, assessment key points are prominent, the flexibility of the assessment process is high, and the assessment content is wide.

The invention provides a city public health emergency rescue auxiliary decision system based on artificial intelligence technology. An unmanned aerial vehicle comprises a positioning module, a camera and a face identification module. The positioning module acquires geographical position information of a current position. The camera photographs a field real-time picture. A background commanding center comprises the components of a receiving module which receives the geographical position information of the current position and a corresponding field real-time picture; a disaster determining module which performs identification on the field real-time picture image for determining a specific field disaster type; a rescue requirement module which analyzes a rescue requirement, a medicament requirement and an equipment requirement according to injury condition characteristics; a wounded person positioning module which controls the unmanned aerial vehicle according to the field real-time picture for searching in a disaster area that cannot be approached through ground traffic; a face identification module which searches the trapped wounded person and determines the geographical position information of the current position when the wounded person exists; a receiving module which receives the transmitted image and the geographical position information of the trapped wounded person; and a medical record calling module which queries the previous medical record of the trapped wounded person according to the image of the trapped wounded person and transmits to field rescue personnel.

The invention provides a system combination model credibility intelligent evaluation method based on deep learning. The system combination model credibility intelligent evaluation method comprises thefollowing steps of obtaining a reference learning sample set, obtaining the reference learning sample set, evaluating uncertainty influence degree, evaluating noise influence degree and evaluating credibility. According to the invention, a deep learning method is applied; uncertainty and influence of noise are comprehensively considered; the credibility evaluation of the to-be-inspected model ismore reliable; a reverse mapping relationship from a simulation learning sample (to-be-inspected model) is applied to a reference learning sample (reference model); a fuzzy phenomenon possibly occurring during forward mapping is avoided, credibility evaluation accuracy is improved, through the deep learning method and the optimization model based on the loss function, implementation difficulty ofsystem combat simulation credibility evaluation is reduced, and adaptive intelligent evaluation and model screening are realized.

The embodiment of the invention provides a cell capacity evaluation method and device, and the method comprises the steps: obtaining a feature vector of a to-be-evaluated cell in a preset historical time period, and enabling the feature vector to comprise a plurality of feature parameters; inputting the feature vector into a pre-trained capacity evaluation model to obtain a cell capacity evaluation result output by the capacity evaluation model; wherein the cell capacity evaluation result indicates whether the cell to be evaluated is in a high-load state in a preset time period; wherein the capacity evaluation model is obtained by training label data of a sample cell serving as a training sample in advance, and the label data comprises a training feature vector of the sample cell in a first preset historical time period and a capacity result of whether the sample cell is in a high-load state in a second preset historical time period after the first preset historical time period. According to the embodiment of the invention, the efficiency and accuracy of cell capacity evaluation are improved.

The invention discloses a remote video teaching quality evaluation method and system based on machine vision. The method comprises the following steps of obtaining a face image, a learning state imageand a classroom scene image of each student; matching the periodically acquired face images with a preset face sample library after 3D transformation to obtain student identity information; transmitting the periodically acquired student learning state images to a pre-trained deep neural network model to obtain the learning behavior of each student; and performing real-time image processing on theclassroom scene image to obtain personnel exception aggregation information. After learning is finished, statistics and analysis are carried out on student identity information and learning behaviors, attendance and learning quality scores and comments of the students are obtained according to attendance and learning quality evaluation rules, and automatic student attendance of remote teaching isachieved; based on the remote teaching monitoring method, automatic attendance checking, automatic learning quality evaluation and teaching order maintenance of students in remote teaching are completed.

The invention relates to the technical field of financial science and technology, and discloses a risk assessment method, device and apparatus and a computer readable storage medium. The risk assessment method comprises the steps that when a subsystem change request is received, acquiring change information according to the subsystem change request; determining a target influence request and a target influence factor according to the change information, and obtaining a historical average request amount of the target influence request; and calculating according to the historical average requestquantity and the target influence factor to obtain an estimated influence request quantity, and determining a corresponding risk level according to the estimated influence request quantity. Accordingto the invention, the change risk assessment efficiency and the accuracy of the change risk assessment result can be improved.

The invention discloses a scanning image detection method, electronic equipment and a computer readable medium. The method comprises the following steps: acquiring a plurality of layers of scanning images of a scanning object; inputting the plurality of layers of scanning images into a quality control network model to obtain image quality detection results of the plurality of layers of scanning images; in response to the fact that the image quality detection result of at least one part of layer scanning images in the multiple layers is abnormal, image abnormal areas are determined from the at least one part of layer scanning images with the abnormity, and the image abnormal areas are marked in the scanning images, so that the image quality problem existing in the at least one part of layer scanning images is prompted. According to the invention, image quality detection results are respectively detected from a plurality of layers of scanning images based on the neural network model, scanning images with quality problems are conveniently and rapidly screened from tens of layers of scanning images or even hundreds of layers of scanning images, and abnormal areas are prompted, so that intelligent evaluation of the quality of the scanning images is realized, and the efficiency and accuracy of the whole process of examination and diagnosis are improved.

The invention relates to an enterprise credit evaluation method and device. As long as the assessment data of evaluation indexes inputted by a user are obtained, and the standard values of the evaluation indexes are obtained, the scores of the evaluation indexes can be calculated; the weight of each evaluation index is determined based on an entropy method, and the comprehensive score of an enterprise to be evaluated can be obtained according to the weight of each evaluation index; and therefore, the intelligent evaluation of the credit evaluation of the enterprise is realized, requirements for intellectualization and massification can be satisfied. Because the weights of the evaluation indexes are determined through the entropy method, rather than empirical evaluation, manual weighting isavoided to the greatest extent, and the objectivity and accuracy of the credit evaluation of the enterprise are improved.

The invention discloses a static power grid safety and reliability assessment method for a dispatcher training simulator. According to the assessment method, static safety analysis software is applied to the assessment on the dispatcher training simulator, analyzed and calculated output results of the static safety analysis software are subjected to expansion, a cycle call and/or event call mechanism is adopted, and finally, assessment indexes applicable to the dispatcher training simulator are obtained. According to the method, the static safety and reliability of a power grid in the current dispatcher training assessment index system is assessed for the first time, and a technical basis which is used for further developing the dispatcher training simulator into an intelligent training system is laid.

The invention provides a property consultant customer follow-up performance evaluation method and system, and a storage medium, and the method comprises the steps: obtaining the follow-up data of a property consultant for a to-be-received customer, obtaining the weight coefficient of each index in the follow-up data based on a pre-built regression model, and carrying out the calculation to obtaina one-time follow-up performance score for the to-be-received customer; dividing the clients into different grades according to the transaction intention, and calculating to obtain a final performancescore by calculating the transaction probabilities of the clients under different transaction intention grades and combining with the performance score followed by the property consultant for all theclients to be received. According to the method, the follow-up data are taken as a core, the clients are divided into different grades according to the transaction intention, and the transaction conditions of the clients with different transaction intention grades are taken as main reference factors, so that the final performance score is finally calculated, and the performance follow-up condition of the property consultant for the clients to be received can be evaluated more accurately.

The invention provides an image evaluation method and device, a computer readable storage medium and electronic equipment, and relates to the technical field of image processing. The image evaluation method comprises the following steps: determining optic cup and optic disc feature information corresponding to a fundus image to be evaluated; determining nerve fiber injury information corresponding to the fundus image to be evaluated; and determining glaucoma assessment information corresponding to the fundus image to be assessed based on the optic cup and optic disc feature information and the nerve fiber injury information. Intelligent evaluation is carried out on the early risk of glaucoma, the severity and the change degree of glaucoma and the like according to the optic cup and optic disc feature information in combination with the nerve fiber injury area, so that doctors are helped to carry out glaucoma diagnosis more accurately.

The invention discloses a sea disaster intelligent monitoring system and method based on data analysis, and belongs to the technical field of deep learning. According to the method, a sea wave prediction model is constructed based on an LSTM algorithm, a network structure is deepened, the algorithm is improved, historical ocean monitoring data is input for repeated iterative training, a prediction model with the maximum mAP value is output, the prediction model is established to evaluate the accuracy of a mechanism, and disaster loss possibly caused by sea waves is output and judged; according to the method, sea wave prediction is established, the marine disaster prevention and coping capacity is improved, the marine early warning public service is well done, different from a complex model needed for model establishment in a numerical forecasting method, sea wave prediction is established macroscopically, and a prediction model is established based on an LSTM network; the method does not need to pay attention to how factors influencing sea waves act on the sea waves, helps to analyze sea wave generation reasons on the basis of a high-precision sea wave prediction model, and achieves intelligent sensing, intelligent evaluation and intelligent control of sea wave disasters.

The invention discloses an outdoor sports evaluation and guidance device. The device comprises a cabinet body, a power supply, universal wheels, a first display screen, a second display screen, and aCPU and accessory circuit assembly; the first display screen and the second display screen are arranged at the front part of the cabinet body, are connected with a CPU and the power supply, display action scores and guidance, and play demonstration videos; and the CPU and accessory circuit assembly is arranged in the cabinet body, is installed in a small case, controls a light supplementing lamp,a visual action sensor, a loudspeaker, the first display screen, the second display screen and stores an action library, performs operational analysis on actions acquired by the visual action sensor,displays scores and wrong actions through the first display screen, and issues instructions and prompts through the loudspeaker. All hardware for sports action evaluation and guidance are integrated,the power supply and the universal wheels are arranged, so that outdoor use is facilitated; and intelligent evaluation and guidance feedback suggestions for sports standardization are achieved, and therefore convenience and professionality of sports training are greatly improved.

The invention discloses a method for determining concrete damaged parts and degrees by carbon fiber cloth. By conductivity and piezoresistive effect of carbon fibers, a certain voltage is applied to electrodes at two ends of a carbon fiber strand with a surface insulating coating; after connection with a computer, changing conditions of current in the carbon fiber strand with the surface insulating coating before and after detonation are obtained to create a database. By measurement of current changes of the carbon fiber strand with the surface insulating coating before and after impacts of explosion, collision and the like, impact position and a damage range and degree can be judged intelligently, and intelligent assessment on a health state of a concrete structure is realized.

The invention discloses a multi-dimensional intelligent clothing pressure test mannequin device, system and method, and relates to the technical field of clothing evaluation and design, and the intelligent clothing pressure test mannequin device comprises a device main body and a human body model; the human body model is circumferentially divided into a plurality of model units along an axis; the device main body comprises a plurality of movable parts and a control base; all the movable parts are circumferentially distributed on the control base around a circle center, and all the movable parts are movably arranged on a straight line where a connecting line between the center points of all the movable parts and the circle center is located; the model units are installed on the movable parts in a one-to-one correspondence mode. The control base is used for driving all the movable parts to move together or respectively, so that the size form of the human body model can be adjusted and changed in a multi-dimensional mode. Therefore, the mannequin device can realize intelligent dynamic and form-adjustable multi-human-body-size clothing pressure test without frequently replacing human body models in clothing pressure test application, and economic and effective clothing functionality evaluation is realized.

The invention discloses a house buying and selling price intelligent evaluation method and system based on cloud computing and big data analysis, electronic equipment and a computer storage medium, and the method comprises the steps: obtaining the basic parameters of a current house, and screening historical transaction houses in a preset time period; comparing the basic parameters of the historical transaction houses with the basic parameters of the current house to screen out similar transaction houses, counting house price influence coefficients corresponding to house floors, decoration degrees and areas, and evaluating the buying and selling price of the current house according to the comprehensive evaluation influence coefficients. intelligent evaluation of the second-hand house buying and selling price is achieved, the defects that an existing second-hand house price evaluation mode is too stylized, not high in flexibility and not high in accuracy are overcome, the accuracy of a second-hand house price evaluation result is improved, then the second-hand house transaction period is shortened, and the rapid transaction requirements of some sellers are met.

The invention discloses an optical fiber transmission quality monitoring device for an optical fiber composite overhead ground wire ice melting through-flow process. The optical fiber transmission quality monitoring device comprises 36 paths of flange panels, an anti-static case, an optical switch, a power supply module, a temperature control unit, a fan I, an industrial personal computer, a touchscreen, a fan II, a main control circuit, a light source module, a fan III, a converter, a power supply switch and a fiber winding disc, according to the optical fiber transmission quality monitoringdevice for the optical fiber composite overhead ground wire ice-melting through-flow process, the influence on the optical fiber transmission quality of a plurality of composite overhead ground wiresin the ice-melting through-flow process can be intelligently evaluated, the detection efficiency is improved, and the reliability of power communication is ensured.