34results about How to "Objective and Accurate Evaluation" patented technology

The method comprises: using super complex number (quaternion) to build a model for color image, which can save the whole information of the color image; using the singular value decomposition of the super complex number to extract the self energy feature of the color image; using the difference between the signaler values in the original image and the distortional image to build the distortion mapping matrix, which is used to evaluate the quality of the color image. The invention can measure the type and level of image distortion so as to accurately evaluate the quality of color image.

The invention belongs to the field of radiotherapy plan evaluation and discloses a machine learning-based radiotherapy plan evaluation method. With the method adopted, the problems of the non-uniformity of standards and susceptibility to subjective deviation of a conventional technology which adopts manual operation to evaluate radiotherapy plans. The method includes the following steps that: pre-processing work such as voxel selection, voxel feature extraction and voxel data annotation, is performed on the DICOM (Digital Imaging and Communication) data of high-quality radiotherapy historicalplans; voxel data are used to train a machine learning model; the model outputs predicted dose values for each voxel in a plan to be evaluated; a two-dimensional DVH prediction curve and a three-dimensional voxel dose prediction distribution map are further generated for each crisis organ; and finally physicists actually evaluate the radiotherapy plan to be evaluated with the reference of the curves and distribution maps. The present invention also discloses a corresponding evaluation system suitable for the objective and accurate evaluation of a radiotherapy plan.

The invention discloses a method for maintainability assessment and weak link identification of a production design stage. The process is to analyze maintainability attributes of a product from a viewpoint of maintenance influence, classify the maintainability attributes and clarify basic analysis and assessment layer of each attribute, and define a maintainability index of the product on the basis so as to assess the maintainability of the product in the design stage. The method for maintainability assessment and weak link identification of the production design stage can improve accuracy, objectivity and pertinence of maintainability assessment, and has the advantage of being capable of identifying the weak link of the product maintainability design.

The present invention relates to a method and a device for assessment of a client activity degree and a storage medium. The method comprises the steps of: collecting an operation behavior of a clientin a preset time period; obtaining scores corresponding to each operation behavior; and calculating an activity degree score of the client in the preset time period according to the scores of the operation behaviors, and assessing an activity degree of the client at a cut-off moment of the preset time period according to the activity degree score. The method and the device for assessment of a client activity degree can objectively and accurately assess a user activity degree and can overcome the influence of subjective factors on assessment of a client activity degree.

The invention discloses a semi-monitoring crowdsourcing marking data integration method facing imbalance of labels. According to the phenomena that (1) the label marking accuracy is not related to objects and (2) the weights of different marking tasks of the same object are the same, a new weighted parameter evaluation method and a marker capability evaluation methods are provided, and the semi-monitoring crowdsourcing marking data integration method facing imbalance of labels. An iteration manner is used for solving, so that estimation for the weighted parameters and the marker capability is more objective and accurate, and an integrated marking result is more accurate; and the method is suitable for different types of crowdsourcing marking data including but not limited to images, texts and videos.

The invention relates to the field of non-invasive measurement, discloses method for measuring a hepatic vein pressure gradient based on portal vein characteristics, and solves the problem that a prior invasive method for measuring portal vein pressures has high risk, high cost and large operation difficulty, while the accuracy of a current clinical non-invasive prediction model is still influenced by various interference factors. The method comprises the following steps of: constructing a portal vessel three-dimensional model by using a CTA layer sequence of a liver cirrhosis portal hypertension patient, and extracting the characteristics of the portal vein; by means of LASSO regression analysis, screening out the vein characteristics closely related to HVPG, and therefore constructing the model based on portal vein characteristics to predict HVPG. The method is suitable for non-invasive measurement of the hepatic vein pressure gradient.

The invention provides a comprehensive evaluation system and method for the user-side power quality. Comprehensive evaluation is performed on the power grid of a power grid according to the category of the electric load of users. The comprehensive evaluation system is composed of monitoring point terminals, a data transmission network and a control platform server, wherein each monitoring point terminal is used for collecting power quality information at each user monitoring point, performing specified mathematical processing and outputting an obtained evaluation index set and a power qualitycomprehensive evaluation result to the data transmission network; the data transmission network is used for receiving the evaluation index set and the power quality comprehensive evaluation result which are outputted by the monitoring point terminals, and realizing two-way data transmission between the monitoring point terminals and between the monitoring point terminals and the control platform server through the Internet; and the control platform server performs information interaction with the monitoring point terminals through the data transmission network on the one hand, and releases thepower quality comprehensive evaluation result to the network on the other hand, thereby facilitating the users to check at any time through a computer or a mobile terminal.

The invention discloses a method and a device for reflecting collaboration degree of at least two participants. The method comprises steps as follows: EEG (electroencephalograph) data of each of the at least two participants are collected in the same interactive scene; EEG data collected at the same time are collected according to timestamp information included in the EEG data; EEG collaboration indexes of every two participants are calculated according to every two of the EEG data collected at the same time; the average value of the EEG collaboration indexes is solved, EEG collaboration indexes of the at least two participants are obtained, and accordingly the collaboration degree of the at least two participants is reflected. EEG data of the at least two participants at the same interactive scene are collected synchronously, the EEG collaborative indexes of the at least two participants are calculated according to the collected EEG data, accordingly, the collaboration degree of the at least two participants can be reflected, and the interaction condition of the participants can be evaluated objectively and accurately.

The invention discloses an evaluation method and device of an acoustic echo cancellation algorithm, terminal equipment and a storage medium, and the method comprises the steps: obtaining a near-end voice signal corresponding to a to-be-tested terminal, obtaining a far-end voice signal corresponding to a reference terminal, and obtaining an echo cancellation signal corresponding to the near-end voice signal; obtaining a first evaluation parameter based on the far-end voice signal and the echo cancellation signal, obtaining a second evaluation parameter based on the near-end voice signal, and evaluating the echo cancellation effect of the to-be-tested terminal based on the first evaluation parameter and the second evaluation parameter. According to the method, the echo cancellation effect ofthe to-be-tested terminal can be objectively and accurately evaluated through the first evaluation parameter and the second evaluation parameter.

The invention relates to a full-reference screen video quality evaluation method based on a spatial-temporal Gabor feature tensor. The full-reference screen video quality evaluation method comprises the following steps of: firstly, respectively giving reference and distorted screen video sequences, and applying a 3D-Gabor filter to the reference and video sequences to obtain a spatial-temporal feature tensor; secondly, calculating the spatial-temporal feature tensor similarity of the reference screen video and the distorted screen video; and finally, acquiring a quality score of the distortedscreen video by using a pooling strategy based on the spatial-temporal feature tensor. The full-reference screen video quality evaluation method provided by the invention is simple in calculation andcan accurately evaluate the screen video quality.

The invention relates to an accumulated hole depth measuring system and method of an engineering machine. The engineering machine is provided with a machine frame, a working head and an operating control part. The working head is connected with the machine frame through a pull rope and can be controlled by the operating control part to conduct hole-forming operation. The hole depth measuring system comprises a controller, a depth measurer and a pull rope stress sensor. The depth measurer is used for measuring the lowering depth of the working head. The pull rope stress sensor is used for sensing the acting force applied to the pull rope by the working head. The controller is used for recording the first lowering depth of the working head when the acting force sensed by the pull rope stress sensor is changed suddenly (when the working head makes contact with the ground), recording the second lowering depth of the working head when the operating control part sends an end signal, and calculating the one-time effective hole-forming depths and the accumulated hole-forming depth according to the first lowering depth and the second lowering depth. According to the accumulated hole depth measuring system and method and the engineering machine with the system, whether the working head makes contact with the ground or not is recognized through the pull rope stress sensor, the one-time effective hole-forming depths are used as measuring objects, and statistical errors can be eliminated.

The invention discloses a method for maintainability assessment and weak link identification of a production design stage. The process is to analyze maintainability attributes of a product from a viewpoint of maintenance influence, classify the maintainability attributes and clarify basic analysis and assessment layer of each attribute, and define a maintainability index of the product on the basis so as to assess the maintainability of the product in the design stage. The method for maintainability assessment and weak link identification of the production design stage can improve accuracy, objectivity and pertinence of maintainability assessment, and has the advantage of being capable of identifying the weak link of the product maintainability design.

The invention discloses a researcher application scientific research college recommendation method, which is characterized by comprising the following steps of 1, performing comprehensive evaluation on a target college to obtain a comprehensive score of the target college; 2, performing application feasibility evaluation on previous examinees to obtain application feasibility scores of the previous examinees; 3, according to the comprehensive score of the target college and the application feasibility score of the previous examinee, clustering the comprehensive score of the target college applied by the previous examinee and the application feasibility score corresponding to the comprehensive score of the target college by adopting a kmeans clustering algorithm to obtain clustering centersof four classes; and 4, decision classification: taking that a certain examinee selects a certain target college as a scheme; and calculating the Euclidean distance between the score of the examineeto apply for the target college, the score of the examinee to apply for the feasibility and the clustering centers of the four classes, classifying the scheme of selecting the target college by the examinee into the class with the minimum Euclidean distance, and if the values of gk1 and gk2 in the class are both greater than 0, selecting the target college by the examinee to recommend.

The invention discloses a bergamot pear pulp crispness detection method based on force-sound synchronous acquisition. The method comprises the specific steps of 1 preparing a bergamot pear sample; 2 carrying out puncture testing and mechanical characteristic parameter extraction; 3 carrying out sound signal AED low-frequency acquisition analysis and parameter extraction; 4 performing high-frequency acquisition and de-noising preprocessing on a sound signal recorder; 5 extracting high-frequency acquisition acoustic time domain characteristic parameters; 6 extracting high-frequency acquisition acoustic frequency domain characteristic parameters; 7 performing sensory evaluation on the crispness of the bergamot pear; 8 analyzing the correlation between the sensory evaluation result and the force-sound characteristic parameters; 9 performing principal component analysis and dimension reduction on the force-sound characteristic parameters; 10 constructing and verifying a multivariate linear regression bergamot pear crispness detection model based on principal components; and 11 constructing and verifying a bergamot pear crispness detection model based on the BP neural network of the principal components. The method is based on force-sound synchronous acquisition, integrates force-sound multi-characteristic parameters, establishes the multivariate linear regression and BP neural network bergamot pear crispness evaluation model, and realizes objective and accurate evaluation of the bergamot pear crispness.

The invention discloses a method and system for evaluating the quality of a photovoltaic module. The evaluation method includes: cleaning a photovoltaic module in a photovoltaic power station, and acquiring a cleaning effective time interval after the cleaning of the photovoltaic module; acquiring the original data of the photovoltaic module; correcting the original data to determine corrected data; training the corrected data and the cleaning effective time interval after the cleaning, establishing a related influence factor expert database and a secondary expert database; comparing the samephotovoltaic module in the related influence factor expert database and the secondary expert database under the cleaning effective time interval after cleaning, and determining the attenuation efficiency of the photovoltaic module; and evaluating the quality of the photovoltaic module according to the attenuation efficiency. The evaluation method and system provided by the invention can improve the quality evaluation accuracy of the photovoltaic module.

The invention relates to the technical field of intelligent driving, and provides a driving system evaluation method and device, computer equipment and a storage medium. According to the invention, the accuracy of evaluating the driving system can be improved. The method comprises the following steps: acquiring actual driving data of a vehicle in each driving risk scene, performing simulation driving on a to-be-evaluated driving system by using the actual driving data corresponding to each driving risk scene, and acquiring the probability that the to-be-evaluated driving system triggers a preset-grade accident in each driving risk scene; and evaluating the driving system according to the probability that the to-be-evaluated driving system triggers the preset-level accident in each driving risk scene.

The invention provides a tumor patient physical and psychological pain index assessment method and system, and the method specifically comprises the following steps: S1, collecting a video of a patient in an observation period, intercepting a to-be-analyzed image, and extracting a face image in the to-be-analyzed image; s2, inputting the face image into a pre-trained neural network body pain and psychological pain recognition model for pain recognition to obtain a first body pain level and a first psychological pain level; s3, automatically detecting and tracking the posture change track of the patient in the observation period video, and obtaining the posture change frequency and a second body pain level; s4, the patient performs self-evaluation according to the psychological pain test questions and the body pain test questions to obtain a second psychological pain grade and a third body pain grade; and S5, calculating a body pain assessment value and a psychological pain assessment value according to a preset weight coefficient. According to the invention, a plurality of methods are adopted to evaluate the patient, and a plurality of evaluation results are integrated to obtain a final evaluation result, so that the evaluation is more objective and accurate.

The invention discloses an evaluation method and device of an acoustic echo cancellation algorithm , terminal equipment and a storage medium, and the method comprises the steps: obtaining a target far-end voice signal, and then obtaining a near-end mixed signal, the near-end mixed signal comprising a first analog reverberation voice signal associated with the near-end voice signal and a second analog reverberation voice signal associated with the target far-end voice signal; and acquiring echo cancellation evaluation parameters obtained in the echo cancellation process based on the target acoustic echo cancellation algorithm, the target far-end voice signal and the near-end mixed signal, and then evaluating the echo cancellation effect of the target acoustic echo cancellation algorithm based on the echo cancellation evaluation parameters. According to the method, the acoustic echo cancellation effect of the acoustic echo cancellation algorithm can be evaluated objectively and accurately.

The invention provides a small intrapulmonary nodule progress evaluation system and method based on deep learning, and relates to the field of medical image processing technology. The method comprisesthe steps of acquiring all lung tomography images in a follow-up process of a small intrapulmonary nodule patient; performing image preprocessing on all the lung tomography images for obtaining preprocessed images; for each small intrapulmonary nodule patient, marking the small intrapulmonary nodules at the same position in each preprocessed image and establishing a nodule growth database; establishing an initial evaluation model according to a preset hyperparameter; training the initial evaluation model accordingi to the nodule growth database for obtaining a progress evaluation model; and inputting the lung tomography images of a to-be-evaluated small intrapulmonary nodule patient into the progress evaluation model at different follow-up time for obtaining growth progress data of the small intrapulmonary nodule of the small intrapulmonary nodule patient, thereby supplying to a doctor for diagnosis reference. The method of the invention can objectively and accurately evaluate changesof the small intrapulmonary nodule and effectively improves evaluation result accuracy.

The invention discloses a method and a device for reflecting the degree of cooperation of at least two participants. Wherein, the method includes: collecting EEG data of each of the at least two participants in the same interaction scenario; aggregating EEG data at the same collection time according to timestamp information included in the EEG data ; calculating the EEG synergy index of every two participants from each of the EEG data at the same acquisition time; and averaging the EEG synergy indexes to obtain the at least two participants' EEG synergy index, thereby reflecting the degree of cooperation of the at least two participants. The present invention reflects the degree of cooperation of the at least two participants by synchronously collecting the EEG data of the at least two participants in the same interaction scenario, and calculating the EEG synergy index of the at least two participants according to the collected EEG data. , so as to be able to objectively and accurately evaluate the interaction between the participants.

The invention provides an evaluation method of spatial distribution of sampling points in food monitoring. The method includes the following steps that a sampling address of each sampling position ina to-be-monitored region is obtained, and the sampling addresses are converted into longitude and latitude coordinates; according to the longitude and latitude coordinates of each sampling position, adistance matrix is configured for the distance between each sampling position and other sampling positions; based on the distance matrix, a distance average value is standardized, and the standardized distance average value is obtained; a sampling position excessive gathering region set is built, the number of effective sampling positions is calculated, and the ratio of the number of the effective sampling positions to the total number of the sampling positions is calculated; the standardized distance average value in a to-be-monitored region and the ratio of the number of the effective sampling positions to the total number of the sampling positions are compared with preset standard values respectively, and according to the comparison results, the rationality of spatial distribution of the sampling positions in the to-be-monitored region is judged. The method can more accurately evaluate the rationality of spatial distribution of the sampling points.

The invention belongs to the technical field of measurement and discloses a method for evaluating a polymer laser marking effect. According to the method for evaluating the polymer laser marking effect disclosed by the invention, an intensity change before and after a material is printed with a laser mark, a color difference change before and after the material is printed with the laser mark or an absolute value of a difference value of the intensity change and the color difference change are used as indexes. The evaluation method disclosed by the invention is simple, rapid and direct to operate and can be used for objectively and accurately evaluating the laser marking effect of a polymer material.

The invention provides a diabetic foot evaluation, detection and protection training system based on VR games. The system comprises a hardware module and a software module. The hardware module is composed of a computer, a wearable 3D display device, a Bluetooth headset, a depth camera, a universal running platform, a rotation evaluation detection table, a platform base, a supporting frame, a safety protection ring, a protection connecting rod, a protection waistband, a sensor and a peripheral circuit. The software module is a diabetic foot evaluation detection and protection training VR game and comprises an evaluation detection part and a protection training part. According to the system, traditional diabetic foot detection evaluation and protection training are integrated into a VR game,and a detection result is given through a game scoring mechanism, so that the evaluation process is more objective and accurate. Besides, compared with boring protection training in reality, VR gamesbring strong sense of presence to the patient, and gamified protection training can greatly improve enthusiasm and initiative of training of the patient, so that a better training effect is achieved.

The invention belongs to the field of EEG signal acquisition and processing, in particular to a classroom teaching evaluation system and method based on an EEG frequency-domain feature index algorithm. The system includes an EEG acquisition device, an IC circuit, an audio and video acquisition device, a data communication device, a data processing and storage device, and the EEG acquisition device and the audio and video acquisition device collect the user's EEG signal and the classroom environment respectively. The audio and video signals, the data processing and storage device, and the collected data are processed and displayed to the classroom teacher, so as to grasp the status of the user in the classroom in time. The beneficial effects of the present invention are as follows: (1) The present invention can record the attention index of the students throughout the process, and provide teachers with objective and accurate evaluation and judgment. (2) The present invention records the classroom teaching situation in the whole process of video and audio recording, which is true and reliable. (3) The present invention can reflect whether the student's attention is concentrated in real time.

The invention discloses a depression tendency evaluation device and system. Wherein, the depression tendency evaluation device includes a processor, which is configured to perform the following steps: receive the emotional test behavior information of the sample user, obtain and mark the depression tendency of the sample user; receive the social interaction network behavior of the sample user when viewing different emotional face images information and eye movement information; extract the social interaction network behavior information and eye movement information features of sample users to form a depression tendency feature set; train a classification model according to the depression tendency feature set and depression tendency; the classification model includes a basic model connected in series layer and a meta-model layer, the basic model layer includes at least two parallel connection classification sub-models; the meta-model layer includes a classification sub-model; the trained classification model is used to evaluate the depression tendency of test users. Combining social interaction network behavior information and eye movement information, it can objectively and accurately evaluate depression tendency under the premise of ensuring personal privacy.

The invention discloses a quality evaluation method and device of an image sample set and a storage medium. The method comprises the following steps: determining face sampling quality associated with a face target in a face sample image, and determining a first evaluation parameter of an image sample set according to the face sampling quality; determining a second evaluation parameter of the image sample set according to the distribution of the face sample images among different personnel categories; according to the number of effective sample images in the image sample set, a third evaluation parameter of the image sample set is determined, and the effective sample images are face sample images suitable for determining categories through a deep learning-based model; and evaluating the quality of the image sample set according to the first evaluation parameter, the second evaluation parameter and the third evaluation parameter.

The invention discloses a nuclear power plant metal part environment promotion fatigue life evaluation method, which comprises the following steps: carrying out metal part fatigue life analysis to obtain a fatigue accumulation use factor corresponding to an analysis position on a metal part; determining a corresponding environmental impact factor calculation formula according to the material type of the metal part; obtaining a time period in a tensile stress state through stress analysis, and obtaining environmental influence factors corresponding to different time points in the tensile stress state according to the calculation formula; obtaining environment influence factors corresponding to one or more stress peak-valley value pairs of the metal part through integral summation operation; and according to the fatigue accumulation use factor and the stress peak-valley value, pairing the corresponding environmental influence factor, and obtaining the environmental promotion fatigue life of the metal part. The nuclear power plant metal part environment promotion fatigue life evaluation method provided by the invention considers the influence of the service environment on the fatigue life of the metal part, so that the evaluation is more objective and accurate.

The invention discloses a method for managing students in a smart classroom. The method includes: capturing facial information of students through a camera, and resonant imaging diodes are arranged around the camera. The reflected light intensity caused by blood flow is used to optically recognize the students' faces to obtain their physiological information; capture the students' face information through the camera, and use the eye positioning technology in face recognition to determine the position of the human eye and capture the blinking action; through the detection Whether the student’s eyes are open or closed is in a state of concentration, and by measuring the face contour or the ratio of the pupils, it is judged whether it is in a state of frontal vision; through mathematical analysis of the student’s facial information collected by the camera, the student’s Concentration status; display the concentration status of all students on the teacher's control terminal.