879 results about "Evaluation finding" patented technology

A video quality evaluation method based on artificial neural network, which belongs to the field of computer digital video processing. The evaluation algorithm computes damage extent of an image by analyzing spatial characters (blur, entropy, blocking effect, frequency-domain energy analysis, saturation) and time behaviors (frame-to-frame differences). Evaluation effect of the algorithm can be effectively modified by using colour space saturation as one of the parameters for non-reference evaluation algorithm. The system is designed based on artificial neural network, therefore, training process and testing process of the network are included in realization of the algorithm. To the selected training sample (video image sequence), firstly extracts six parameters of the sample, then obtains expected output (subjective evaluation result) in training through subjective evaluation. Characteristic parameters of the training sample and the corresponding subjective evaluation result are inputted to the artificial neural network as training parameters. The experiment shows that evaluation result obtained by the objective evaluation system is highly-consistent with visual sense of human eyes.

The invention discloses a question-answer pair quality evaluation method including the steps of clustering input question-answer pairs according to question contents to obtain a cluster including questions with same or similar semantic meanings and answers to the questions; performing quality evaluation between the question-answer pairs and quality evaluation in the question-answer pairs to the cluster and respectively obtaining the quality evaluation result between the question-answer pairs and the quality evaluation result in the question-answer pairs; inosculating the quality evaluation result between the question-answer pairs and the quality evaluation result in the question-answer pairs and outputting the question-answer pairs with high quality. The invention also provides a question-answer pair quality evaluation system so as to realize more effective question-answer pair quality evaluation and improve the commonality of quality evaluation.

The invention puts forward a power distribution equipment state visualization platform based on big data. The platform comprises a data processing module, a data analysis module and an evaluation module, wherein the data processing module is used for obtaining multi-platform data, processing the multi-platform data and displaying the processed data; the data analysis module is used for carrying out big data integration, storage and retrieval and data mining analysis; and the evaluation module is used for generating a power distribution equipment evaluation model based on the big data, evaluating the power distribution equipment according to the power distribution equipment evaluation module, and generating a corresponding processing strategy according to an evaluation result. By use of theplatform, the business requirements of intensive development and lean management can be met, the multisource information interaction fusion ability of the equipment is improved, the full view real-time perception, and the multidimensional intelligent monitoring and control of the power distribution equipment can be realized, equipment operation risks can be prevented in advance, reaction speed for emergency events can be improved, and the full life cycle of the equipment can be subjected to management transparency and high efficiency.

The invention provides a quantitative characterization method of low penetration double-medium sandstone oil reservoir microscopic aperture structure, which comprises the following steps: selecting experiment samples, effectively combining various experiments, distributing samples, processing and analyzing experiment test data, combining macroscopic background and microscopic rock core, and combining static state analysis and dynamic production reality, thereby realizing quantitative characterization of ultra-low penetration double-medium sandstone oil reservoir microscopic aperture structure from qualitative analysis and semi-quantitative evaluation. The invention has the advantages that more comprehensive influence factors and micro crack, aperture throat parameter and nuclear magnetic resonance movable fluid parameter are considered, so the characterization result can better reflect change characteristics of ultra-low penetration double-medium sandstone oil reservoir microscopic aperture structure, which are consistent to the production exploitation real cases of the oil field, thereby effectively avoiding one-sidedness and limitation of single aspect evaluation result.

There is provided a device capable of evaluating a composition by a computer in the Internet. First, a task of a composition corresponding to the grade level of a learner and evaluation tasks are presented on the Internet. A compositional essay created by the learner according to the presented tasks and terms is evaluated by multiple methods associated with the evaluation tasks and the evaluation result is distributed to a grader responsible for evaluating the learner by means such as e-mail. The grader adds a comment to the evaluation result, records it in the server on the Internet, and displays the evaluation result in a graph or the like so that the learner can easily know the evaluation result. The apparatus for grading and evaluating compositional essays of the present invention is characterized in that (1) a compositional essay is divided into multiple fields such as structure, subject matter, expression, and topic and each of these fields is evaluated by the presence or lack of specified keywords and (2) the individuality of the content is evaluated by the amount and range of unique vocabulary contained in the compositional essay.

The invention relates to a method for objectively and quantifiably evaluating noise fret degree in a vehicle based on an auditory model, in particular to an evaluation method of psychoacoustics and vehicle sound quality. The method comprises the following steps: designing a dummy head model; imitating a processing mechanism of the middle ear and the inner ear of a human body to the sound by usingan auditory peripheral calculation model; collecting vehicle noise signals under the working conditions of uniform, accelerated and idle speed; pre-treating the noise sample and processing the loudness in specification; obtaining a psychoacoustics parameter by using a sound quality calculation model; obtaining subjective evaluation result test data by using a grouped and paired comparison method;calculating and painting a correlated scatter plot chart between each parameter and the ranking value of the subjective evaluation result; and analyzing and calculating to obtain the objectively quantifiable model of the subjective fret degree under each working condition. The invention can realize the psychoacoustic parameter calculation of objectively evaluating the sound quality with differentvehicle types, gears and speeds, wherein the calculated value has good pertinence and consistency with the evaluated result of the subjective evaluation method. The invention has stable evaluated result and high reliability, and can improve the sound quality and competitiveness of vehicles combined with the design of new CAE cars.

The invention discloses a method for evaluating the implementation quality of a software process, which belongs to the field of computer software engineering. The method comprises the following steps that: 1) a user selects an evaluation model or a standard of the software process from an evaluation standard library by using an evaluation standard selection module; 2) an index system establishment module establishes an measurement index system by adopting a target-problem-measurement method or a utility software measurement method; 3) an index measurement data acquisition module performs data acquisition on the software process to be evaluated according to the established measurement index system, and simultaneously, an index weight determination module determines the weight of each measurement index according to the established measurement index system; 4) a comprehensive evaluation computing module performs numerical value standardization and form unitization on the acquired data; and 5) the comprehensive evaluation computing module evaluates the processed data by adopting a fuzzy comprehensive evaluation method and outputs the evaluation result. The method not only ensures flexibility and the strictness of the result, but also ensures the accuracy of the evaluation process and the validity of the evaluation result.

The invention relates to a testing device and a testing method of a lane departure warning system. The testing device is characterized by comprising image sensors, an image acquisition unit, a vehicle-mounted CAN (Controller Area Network) unit and a data processing unit, wherein the image sensors are fixed at both sides above a vehicle and used for acquiring images of the road surface, wherein the plane that the image sensors are located are parallel to the road surface; the image acquisition unit is used for converting the road surface image information acquired by the image sensors into digital information; the vehicle-mounted CAN unit provides vehicle speed information in original vehicle information and warning time information provided by the lane departure warning system to be tested; and the data processing unit is used for working out the distance from one point on the vehicle body to the lane line and the off-line speed at the warning time under a world coordinate system according to the lane-line containing road surface information acquired by the image acquisition unit by combining the vehicle speed and the warning time information provided by the vehicle-mounted CAN unit. The invention has low cost and high authenticity degree of a tested evaluating result and is suitable for testing various lane departure warning systems.

The invention belongs to the field of computer vision and relates to a quantified evaluation method of image mosaic algorithms. The method comprises the following steps: carrying out mosaic on mosaic sequence images by adopting different mosaic algorithms to be evaluated so as to obtain mosaic composite images; carrying out overall statistics on the mosaic composite images and computing a global evaluation index; selecting corresponding mosaic sequence images as reference images in allusion to local mosaic composite images so as to carry out reference image quality evaluation and compute a local evaluation index; and constructing image mosaic evaluation index system levels by adopting a multi-index comprehensive evaluation method, determining the weighting coefficients of the indexes according to the mosaic requirement and purpose, normalizing the evaluation indexes and carrying out weighted aggregation step by step to finally obtain a comprehensive evaluation result. Through the quantified evaluation method of the image mosaic algorithms, the difficulties existing in the current mosaic evaluation algorithms are overcome; and the evaluation result fits the subjective judgment results of people and has objectivity, consistency and stability. The quantified evaluation method of the image mosaic algorithms can also be used for the quantified comprehensive evaluation of the algorithms such as image fusion and the like.

The invention provides a grid security comprehensive evaluation method which includes that a set of complete two-stage in-advance comprehensive evaluation index system and an each-stage security evaluation index calculating method are built aiming at the requirement of grid security operation evaluation, a grid security comprehensive evaluation model based on a gray area correlation analysis method and the game theory is further provided, initial evaluation is conducted on each one-stage index by the model, an obtained evaluation result is subjected to comprehensive evaluation, a correlation coefficient matrix of each one-stage index is determined by adopting the gray area correlation analysis method, weights are obtained by utilizing a game collection model pair analytic hierarchy process (AHP), an artificial neural network (ANN) and an entropy weight method and are objectively combined to obtain a combined weight, initial evaluation is conducted on each one-stage index, the AHP is adopted to determine a one-stage index weight, and the one-stage index weight and an initial evaluation result are subjected to weighing calculation to further obtain a grid security comprehensive evaluation result, namely the grid security quality ordering.

The invention discloses a method and device for examining service quality, and the method comprises the steps: obtaining a to-be-detected audio file; cutting a to-be-examined segment from a voice text corresponding to an audio file; comparing the cut to-be-examined segment with a keyword in a preset database; judging the service quality based on a comparison result, and generating a quality examination result. The invention also discloses a device for examining service quality. According to the technical scheme of the invention, the method irons out the defects of difference and simplification of manual examination, can achieve the automatic evaluation of the service quality of the customer service staff, and is more accurate and reliable in evaluation result.

The invention provides a method for evaluating beautifulness of human faces based on video. The method is achieved by following steps: (1) capturing the face information by video; (2) effectively detecting the face according to the captured information by a cascade classifier based on haar-like characteristics; locating the eyes and the lips on the basis of the face detection, including detecting eyes by adopting a Sobel edge detection operator and a region growing method and determining the boundary of the lips according to the projection of red pixel dots in the face image; (4) extracting the face contour by adopting Snake model; and (5) comparing the extracted information with a face beautifulness standard library to determine the face beautifulness evaluation result. The method can achieve the real-time face beautifulness evaluation by capturing the face video information by a computer, and training to obtain the beautifulness classification standard according to a large amount of face samples.

The invention relates to the technical field of underground road bituminous pavement service performance evaluation. In order to make the evaluation result objective, the effective scientific decision can be provided for the road maintenance and repair department. In order to fulfill the aim, the adopted technical scheme is as follows: the entropy weight-based underground road bituminous pavement service performance evaluation method comprises the following steps of: 1. determining a composite underground road pavement performance integrated evaluation index system, namely 1.1. determining evaluation indexes and evaluation standards, 1.1.1. determining underground road bituminous pavement damage condition evaluation indexes and standards, 1.1.2. determining composite underground road pavement driving quality evaluation indexes and standards, and 1.1.3. determining composite underground road pavement safety performance evaluation index and standards; 1.2, establishing a comprehensive evaluation model; and 2. performing a composite underground road pavement service performance evaluation method. The method is mainly applied to the underground road bituminous pavement service performance evaluation.

The invention discloses a three-dimensional image objective quality evaluation method, which comprises the following steps: respectively carrying out wavelet transformation on left view point images and right view point images of undistorted three-dimensional images and distorted three-dimensional images; extracting characteristic values of each sub band; carrying out similarity measurement on the characteristic values; determining the weight factors of each sub band by contrast sensitive functions; then, realizing the evaluation on the three-dimensional sensing quality through evaluating the absolute difference image similarity of left images and right images of the undistorted three-dimensional images and the distorted three-dimensional images; and finally, combining the quality of the left images and the right images and the three-dimensional sensing quality to obtain the final evaluation results of the three-dimensional image quality. The invention has the advantages that the human eye visual characteristics such as human visual sensitivity bandpass, the multi-channel effect, the three-dimensional sensation and the like are utilized, the three-dimensional sensation is simultaneously evaluated on the basis of the evaluation on the quality of the left view point images and the right view point images, the influence of the three-dimensional sensation in the three-dimensional images on the final three-dimensional image quality is merged into an evaluation model, and the correlativity of the objective evaluation results and the subjective sensation is improved.

The invention relates to a shale reservoir compressibility evaluation method based on a support vector machine technology. The method comprises the following steps: (1) mineral composition quantitative analysis and uniaxial compressive test are firstly carried out; (2) logging characteristic parameters for recognizing a crack are extracted; (3) maximum and minimum horizontal principal stress in different layers is calculated through a combined spring model, and a stress sensitivity degree is then calculated; (4) a compressibility evaluation model is built; and (5) discrete layer stratum compressibility evaluation sample space is then built, and a relationship between a compressibility evaluation result and different response logging curves is subjected to correlation analysis. The shale reservoir compressibility evaluation method based on the support vector machine technology has the beneficial effects that compressibility influencing factors are considered perfectly, the shale gas reservoir compressibility model is built from three aspects of a brittleness index, a natural crack development degree and the stress sensitivity, insufficient consideration on the factors by the existing evaluation method is remedied, and the comprehensive ability of the shale to form a complex crack network during volume cracking can be better reflected.

The invention provides a power secondary equipment risk assessment method and a system thereof. By building a calculation model for secondary equipment maintenance state values in advance, the maintenance state values of secondary equipment can be calculated according to the maintenance state parameters of the power secondary equipment. By building a secondary equipment fault probability curve, the maintenance state values are converted into the fault probabilities of the secondary equipment. Then, by building a calculation model for secondary equipment fault loss values, corresponding probable losses caused by all kinds of faults to the secondary equipment are calculated. The products of the fault loss values and the fault probabilities are taken as the risk values of the secondary equipment. Secondary equipment state assessment is closely correlated with risk assessment through the average fault probability of the equipment. The current operation risk of the equipment can be obtained through a state assessment result. Therefore, operators can aim at and well do the operation and maintenance of the equipment according to the calculation results of the risk values, secondary professional operation management can be optimized and objective bases can be provided for equipment type selection and whether the equipment is required to be replaced or not.

The invention discloses a method for evaluating the simulation imaging of a multi-mode SAR (Synthetic Aperture Radar), which mainly solves the problems of poor adaptability to different operating modes, complex experiment process and long experiment time in the prior art. The method comprises the following steps of: firstly, selecting an operating mode, inputting the parameters of a radar and the motion parameters of a carrier, loading a simulation scene and setting coordinates; secondly, setting a simulation radar echo signal according to a system environment; thirdly, imaging the radar echo signal to obtain a slant-range image; fourthly, geometrically correcting the slant-range image by using a three-dimensional geometric correction method to obtain a ground-range image; and finally, evaluating the quality of the ground-range image, and feeding back and correcting system parameters according the evaluation results so as to provide a feasible basis for a latter semi-physical simulation experiment. The method is applicable to three operating modes including a side looking mode, a slant looking mode and a scanning mode; only a plurality of parameters need to be input during operation, so that the experiment process can be simplified, the experiment time is saved, and the method can be used in a ground simulation experiment of SAR system design.

The invention relates to a rock wettability evaluating method used for petroleum drilling and exploration, which utilizes the frequency dispersion character of rock electrical parameter to conduct reservoir rock wettability evaluating. The dispersion information of phase has closer relationship with the wettability comparing with the resistivity; therefore the evaluating result is more accurate and reliable. The method has the characters of being simple, visual and convenient, which doesn't need special experiment device and the experiment period is short, the maneuverability is strong, the experiment process is simple, and can be conducted under normal temperature and pressure, and which also can be conducted under stimulating the high temperature and pressure of reservoir condition.

The invention provides a fingerprint identification method, which comprises the following steps of, in the process of identifying a fingerprint by utilizing a fingerprint identification device, first collecting the fingerprint, and then carrying out quality evaluation on a collected fingerprint image, and outputting a quality evaluation result onto a screen. The invention provides the fingerprint identification method; a user is enabled to intuitively know image quality; moreover, the identification success rate is improved; the fingerprint identification method is easy to realize; moreover, the execution efficiency is higher.

The present invention discloses an order answering willingness evaluation method and a device for drivers in an online taxi service platform. The method comprises the steps of obtaining training samples, wherein each training sample comprises the order information, the driver state information and the information of whether a driver answers an order or not; obtaining a decision tree model through the training of training samples; according to the decision tree model, converting the order information and the driver state information of each of the training samples into attribute vectors so as to obtain converted training samples; according to the converted training samples, training to obtain a driver order-answering probability prediction model; according to the driver order-answering probability prediction model, determining the order-answering willingness of a driver. According to the technical scheme of the invention, the accuracy of evaluation results is improved.

The invention discloses a method for displaying the evaluation data of a nuclear radiation aftermath. A radioactive release source item is analyzed and calculated according to the state of the power plant of a nuclear power station, an accident aftermath which is possibly generated after an accident occurs to the nuclear power station is forecasted and calculated according to a quick evaluation mode, a single-module mode and a fine evaluation mode, and the calculated aftermath evaluation result is written into a text file; then, these text data are respectively classified according to three modes of the quick evaluation mode, the single-module mode and the fine evaluation mode, are written on a corresponding grid chart layer of a selected mode by selecting and switching at least one mode in the three modes and are represented in the form of arrowheads with different colors and / or changes. The invention combines the parameter information of the geography, the population, the weather and the like around the nuclear power station and intuitively reflects the aftermath which is possibly caused after the accident occurs to the nuclear power station.

The invention discloses a cancer chemosensitivity prediction technique based on a molecular subnet and a random forest classifier. The method is characterized by comprising the steps of fusing data of oncogene expression profile, information of tumor mutation genome information and information of protein-protein interaction group, and excavating carcinogenic and cancer suppressor gene molecular subnets to realize feature extraction; taking the feature extraction as an input feature, designing a training model based on a random forest algorithm, and using the training model to be used for the testing of an independent test set, so as to obtain a chemosensitivity assessment of a patient. If the method provided by the invention is used for screening patients with effective chemotherapy effects before chemotherapy, the method has a significant meaning on cancer therapy.

The invention relates to an image capturing apparatus, an image capturing method and a computer program. An image capturing apparatus includes an image pickup unit configured to obtain an image; a face detecting unit configured to detect a face of a photographic subject included in the image; an attribute detecting unit configured to detect attribute information of the face; an evaluation unit configured to evaluate a degree of intimacy between a plurality of photographic subjects based on a plurality of items of attribute information detected by the attribute detecting unit from faces of the plurality of photographic subjects, the faces being detected by the face detecting unit; and a control unit configured to cause the image pickup unit to capture an image of the plurality of photographic subjects based on an evaluation result obtained by the evaluation unit.

The invention relates to a security risk assessment and early warning method for a high-speed railway tunnel during operation period. The method comprises the first step of constructing an evaluationbasis, including a risk rating assessment standard, an evaluation index system and an early warning mechanism establishment: the risk rating assessment standard includes a risk possibility assessmentstandard and a risk consequence severity rating assessment standard. The risk rating assessment is based on the risk probability rating as the ordinate, and the risk consequence severity rating as theabscissa to construct a risk assessment matrix. The evaluation index system is established by the hazard factors of the four aspects of "human- things-management-environment ", and constructs the risk probability membership function of the hazard factors. The early warning mechanism is established by four-color early warning. The second step of risk rating assessment is quantitatively calculatedbased on the membership function and the second-level fuzzy comprehensive evaluation model, and conducted combining the risk consequence severity rating assessment standard and the risk rating assessment matrix. The third step of determining the early warning rating: obtained by coupling the superposition analysis risk rating and the early warning indicator risk rating. The beneficial effects of the security risk assessment and early warning method for a high-speed railway tunnel during operation period are that the evaluation results are quantified, and the decision is based on science.

The invention relates to the field of passive radar, in particular to a software radio conception based broadband cognitive passive radar system architecture which has an environmental perception capability, a broadband sampling capability, a high-performance digital signal processing capability and a dynamic receiver parameter regulation capability. The method includes: step one, establishing a signal model which comprises non-orthogonal transmission signals, fading channels and direct wave and target echo receiving signals; step two, unifying a fuzzy function, Cramer-Rao bound and detection performances to a general detection theoretical framework; step three, assessing results based on a performance bound given by an assessment system; step four, improving signal quality of a direct wave channel and a target echo channel according to own characteristics of a mobile communication irradiation source. The method is mainly applied to design and manufacture of passive radar systems.

The invention discloses a TFDS (Train Coach Machine Vision Detection System) image quality evaluation method. The method comprises the following steps: calculating the definition S of a required-to-be-evaluated image; calculating the regional saturation Sa of the required-to-be-evaluated image; calculating the dispersity sp of the required-to-be-evaluated image; calculating the dark region standard deviation st of the required-to-be-evaluated image; and according to the calculated definition S, regional saturation Sa, dispersity sp and dark region standard deviation st of the required-to-be-evaluated image, calculating the comprehensive image-quality evaluation f of the required-to-be-evaluated image. Accordingly, the invention also discloses a TFDS image quality evaluation system, which can automatically complete the quality evaluation on TFDS images, can carry out continuous uninterrupted evaluation on any number of images, and also can carry out comprehensive evaluation on a single image, then automatically give image quality evaluation results at real time, thereby solving the problem that evaluation results are non-uniform because of the differences of human factors.

A neighboring object information acquisition device comprises a distance measuring unit measuring a quantity equivalent to a distance to a neighboring object in a predetermined direction. A storage unit stores a sequence of points indicating results of the measurement performed multiple times. An object detection unit detects existence of the object based on the sequence of points. An approximation unit outputs an approximation of the sequence of points by applying a curve or a straight line, so that an approximate curve or an approximate straight line is derived. An evaluation unit outputs a result of evaluation of a reliability of the sequence of points. A determination unit determines object information by selecting one of information derived from the sequence of points and information derived from the result of approximation in accordance with the result of evaluation.

The invention discloses a performance test and evaluation method and device, terminal equipment and a storage medium. The performance test and evaluation method includes the steps that a performance test is conducted on a system to obtain test values of at least two performance indexes; a standardization conversion function is adopted to standardize the test value of each performance index to obtain a standard value of the performance index; a weighted operation algorithm is adopted to conduct weighted operation on the standard values of the performance indexes to obtain a performance test andevaluation value; based on the performance test and evaluation value, a preset evaluation score table is inquired to determine an evaluation score range corresponding to the performance test and evaluation value, and a system performance evaluation result is obtained. The performance test and evaluation method can reflect the system performance test condition as a whole, and thus non-professionalpersons can know the system performance test condition according to the system performance evaluation result.

The invention discloses a method to divide an ecological function regionalization by using a geological information system and the remote sensing technique, comprising the following steps. The first step is to get an evaluation index information map series; the second step is to do quantitative analysis and evaluation to every evaluation index by using the GIS software; the third step is to comprehensively evaluate the regional ecological function; the fourth step is to regionalize the ecological function. A landscape evaluation index is added to the ecological function regionalization. The real-time geological information data is obtained by using the RS; an attribute value of the evaluation index is calculated and output by using the space analysis and the data processing ability of the GIS software; the evaluation value is batch-computed and classified by using the VBA programming in Excel; finally, the results of the ecological function regionalization can be got by using the GIS software. By the quantitative analysis in the whole process and the normative computer operational calculation, the invention reduces the subjective faults in the normal ecological regionalization method and the objective evaluation results of the ecological function can be generated to get a subjective and reasonable regionalization conclusion.

The invention discloses a non-reference asymmetric distorted stereo image objective quality assessment method. The method comprises the following steps: firstly, filtering a left viewpoint image and a right viewpoint image of a to-be-assessed asymmetric distorted stereo image respectively by virtue of a Gabor filter and a Gaussian filter so as to obtain corresponding Gabor filter image and Gaussian image; then, establishing a valid mathematical model integrated with asymmetric distorted stereo visual perception characteristics by simulating a human visual system, and obtaining a left and right viewpoint characteristic integrated image of the to-be-assessed asymmetric distorted stereo image according to the mathematical model; then, carrying out local binarization model operation on the left and right viewpoint characteristic integrated image so as to obtain a local binarization model structural characteristic image, and obtaining a histogram statistic characteristic vector by virtue of a histogram statistic method; and finally, according to the histogram statistic characteristic vector, forecasting an objective quality assessment predicted value by virtue support vector regression. The objective quality assessment method disclosed by the invention has the advantage that the correlation between an objective assessment result and subjective perception can be effectively improved.