145results about How to "Effective assistance" patented technology

The invention provides a GNSS/INS/vehicle integrated navigation method for agricultural machinery operation in the technical field of navigation. The method comprises the following steps: S1, inertial navigation calculation is carried out after correction of zero offset of an inertial measurement unit (IMU), and a state transition matrix and a system covariance matrix are calculated through Kalman filtering; S2, whether GNSS information is updated is judged; if the GNSS information is updated, the GNSS information is extrapolated, filtering estimation is carried out by taking the position and speed differences between INS and GNSS as observations, the dynamic condition of the carrier is judged, correction platform error and IMU zero offset error are fed back, and the method returns to S1 for loop execution; or, the current information is the position, speed and attitude information of the carrier; and S3, whether vehicle information is updated is judged; if the vehicle information is updated, the vehicle information is extrapolated, filtering estimation is carried out by taking the speed difference between INS and the vehicle as an observation, and correction platform error and IMU zero offset error are fed back; or, the current information is the position, speed and attitude information of the carrier. The method has high navigation accuracy, and can achieve high navigation accuracy with a low-cost IMU.

The invention discloses a deep learning-based diabetic retina image classification method and system in the technical field of artificial intelligence. The method comprises steps: a fundus image is acquired; the same fundus image is imported to a microvascular tumor-like lesion recognition model, a hemorrhagic lesion recognition model and an exudative lesion recognition model for recognition; andaccording to recognition results, lesion feature information is extracted, a trained SVM classifier is then adopted to classify the extracted lesion feature information, and a classification result isacquired, wherein the microvascular tumor-like lesion recognition model is obtained when a microvascular tumor-like lesion candidate area in the fundus image is extracted and is then inputted to a CNN model for training, and the hemorrhagic lesion recognition model and the exudative lesion recognition model are obtained when a hemorrhagic lesion area and an exudative lesion area in the fundus image are marked and are then inputted to an FCN model for training. The requirements on the description ability of the network model are reduced, the model is easy to train, a lesion focus area is positioned and delineated for different lesions, and clinical screening by a doctor is facilitated.

The invention relates to a method for evaluating the online commodity assessment quality based on the Bayesian network, and belongs to the technical field of online commodity assessment and uncertainty reasoning. The method comprises the steps of firstly performing standardization processing on online commodity assessment data, determining an online commodity assessment quality measurement criterion, acquiring an eigenvalue vector and building an eigenvalue matrix; thus acquiring a graph structure of the Bayesian network, and acquiring a probability parameter table set; and finally, performing probabilistic reasoning on an assessment quality value, taking the maximum probability weighted value and a corresponding assessment quality value, finally acquiring an assessment quality measurement value, building an assessment quality measurement value set by assessment quality measurement values of the same commodity, sorting the assessment data of the same commodity according to the assessment quality measurement value, and acquiring an evaluation result. The invention can provide an important assessment quality evaluating method for a third-party platform, and the comment display sequence can be improved in the user perspective, thereby enabling users to check high-quality comment information more conveniently.

The invention discloses a station intelligent video monitoring module, system and method, and a storage medium. The module comprises multiple video acquisition terminals for acquiring video images, avideo analysis server for automatically analyzing various abnormal behavior and an alarm unit, wherein the video analysis server includes a rising identification module, a gathering identification module and a fighting identification module; and the gathering identification module can count the number of people based on head-and-shoulder detection or detect the density of a crowd based on MID by distinguishing the sizes of scenes. According to the invention, a video can be detected without interruption in an around-the-clock manner and abnormalities in a monitoring picture are automatically discovered. The module, method and system can be applied to station networking, strengthen technical prevention and improve the working efficiency of station supervisors at the same time. An alert judgement can be made when the people rise, the sizes of monitoring areas are distinguished, the crowd number or the crowd density are calculated respectively by use of different algorithms, and the calculation precision and the efficiency are improved.

The present invention discloses an active contour blood vessel extraction method based on multi-feature Gaussian fitting and meanwhile, also discloses a related system. A local phase vascular enhancement algorithm is used for carrying out vascular enhancement processing on an original retina image so as to stand out an area where a blood vessel is positioned and reduce unevenness of an image gray scale; corresponding pixel values in a vascular enhancement result graph and an original gray scale graph are used as two mutually independent random variables for constructing a new energy functional active blood vessel segmentation algorithm based on local Gaussian fitting, meanwhile, a regular item is introduced to punish unsmooth performance of a blood vessel contour and an unreasonable length of a contour curve, and local details of the blood vessel contour are properly kept; and the segmentation algorithm is introduced into a variational level set solution frame so as to implement full-automatic extraction of the blood vessel contour. According to the active contour blood vessel extraction method disclosed by the present invention, vascular tissues in the retina image can be more accurately and comprehensively extracted and effective assistance is provided for treatment of ocular diseases.

A simulation experiment system of Principles of Computer Composition comprises a single module experiment simulation subsystem and a whole machine experiment simulation subsystem, wherein the single module experiment simulation subsystem includes a register group module simulation unit, an universal register module simulation unit, an arithmetic unit module simulation unit, a memory and bus module simulation unit, an instruction unit simulation unit, a microprogrammed controller module simulation unit and a sequence and start-stop module simulation unit; the single module experiment simulation subsystem includes an initial module, a switch button detection module and a switch motion operating module; the whole machine experiment simulation subsystem includes an initial module, an operational mode identification module, an instruction fetch module, an instruction analysis module and an instruction executing module. The invention provides a simulation experiment system of Principles of Computer Composition which is cost-cutting and can effectively meet the all requirements of assistant teaching experiments.

The invention relates to a jet spinning apparatus (5) for producing a thread (20) by means of a circulating airflow, having a hollow spinning cone (19) which is arranged in a spinning housing (15), and having two separate groups of blown air nozzles (25, 30) which can be loaded with compressed air independently of one another, wherein the strength of a vacuum flow which acts on a sliver inlet opening (22) during the spinning process can be set via the arrangement of a first group of blown air nozzles (25) and the strength of an airflow which circulates in the region of the spinning cone (19) can be predefined via the arrangement of a second group of blown air nozzles (30). There is provision according to the invention for the blown air nozzles (25) of the first group to be arranged offset at a spacing (b) with regard to the longitudinal centre axis (24) of the jet spinning apparatus (5), with the result that an airflow can be introduced into the jet spinning apparatus (5) via the blown air nozzles (25) during the spinning process, which airflow has a tangential blown air component in order to assist the airflow which circulates in the region of the spinning cone (19).

The invention discloses an automatic synthesis method for a document-based library function code model. The method comprises the steps that 1, usable information is extracted from a document; 2, a natural language processing tool is used for generating a sentence syntax tree; 3, the syntax tree generated in the step 2 is structurally converted to generate a plurality of syntax tree variants; 4, the syntax tress generated in the step 3 are analyzed, parameters, program structures and operational semantics in the syntax trees are recognized, and candidate code models are generated; 5, the candidate models generated in the step 4 are verified, and the candidate models with inconsistent behaviors with an original class library are deleted. The natural language processing technology and the automatic testing technology are adopted in a synchronized mode, a code model is generated for a Java container successfully, the generated code model can effectively improve the correctness and efficiency of other program analysis technologies, and the problem that analysis is hard due to the fact that class library source codes are lost or excessively complex in the program analysis process is solved.

The invention discloses a driving assisting method and device and electronic equipment. The driving assisting method comprises the steps that a first video of a current road section is acquired; on the basis of the first video, parameter information of a current vehicle is used, and the video is controlled to be played to make the position of a vehicle in the video matched with the position of thecurrent vehicle, wherein the parameter information at least comprises one of position information and vehicle speed information. According to the method, the existing first video is acquired, and then the video is controlled to be played on the basis of the first video and the parameter information of the current vehicle, so that the position of the vehicle in the video is matched with the position of the current vehicle, and the position synchronization of the video and the vehicle is achieved. In this way, a driver can view field information in the first video, the road condition information corresponding to the current road section is obtained, and potential safety hazards caused by poor road conditions are avoided. Therefore, effective assistance can be provided for users under severeroad conditions, and the occurrence of safety accidents caused by blocking of the sight of the driver is reduced.

The invention relates to an electric energy data estimation method which comprises the following steps of: (1) original sample data collection and analysis: collecting and preprocessing all court data of a power supply company; (2) classifying all the court data of the power supply company according to court characteristics by using a K-means clustering method, and dividing the courts in the administrative region of the power supply company into K' types with different characteristics; (3) associating each type of typical court basic data with a predicted value, and establishing a mathematical prediction model by using a linear regression method; and (4) inputting the data to be predicted into a model to obtain and output a reasonable required predicted characteristic data predicted value so as to obtain the reasonable required predicted characteristic data predicted value of each type of court. The electric energy data estimation method provides effective assistance for power supply operation by outputting reasonable required predicted characteristic data predicted value.

The invention relates to a biofuel oil-resistant fluorine rubber composition. The biofuel oil-resistant fluorine rubber composition consists of the following raw materials in parts by weight: 100 parts of DAI-ELG-902 fluorine rubber, 1-2 parts of 2,5-ditertbutyl peroxide-2,5-methylhexane, 2-5 parts of TAIC triallyl isocyanurate, 15-30 parts of N990 thermal cracking process carbon black, 1.5 parts of WS-2801 and 3-6 parts of L-5FPTFE powder. The biofuel oil-resistant fluorine rubber composition is high in tolerance under a use environment of the biofuel oil and wide in applicable engine range, and has market potential under the widespread condition of the biofuel oil in the future.

The invention discloses an on-line surrounding rock strength identification method of hard rock heading equipment. The strength of surrounding rock of the heading face is identified through an existing surrounding rock cutting model according to sensing information of the heading equipment. According to the method, the problems that the method for detecting the rock strength through surrounding rock sampling is high in cost and poor in real-time performance are solved, and the strength of the surrounding rock can be identified in real time according to the sensing information of the heading machine; the problem that in the actual construction process, constructors highly depend on individual experience to judge the strength condition of the surrounding rock is effectively processed, dependency of the constructors on experience can be reduced, and then it is guaranteed that construction is safer, more reliable and more efficient; signals are processed by adopting an interative least square method, the calculation amount is decreased, the identification precision is improved, and real-time identification on the strength of the surrounding rock of the heading face of the heading equipment is promoted.

The invention discloses an environment comprehensive evaluation and prediction method based on the remote sensing images, and the method comprises the steps of collecting a satellite remote sensing image and the environment data of a target region through a data information system, and building a basic database; then, according to the basic database, obtaining the parameters required for establishing an environment simulation prediction model; establishing an environment simulation prediction model based on the basic database and the parameters; simulating the space-time distribution of the pollutant concentration through the environment simulation prediction model; and fiinally performing big data analysis on the simulation result and importing the simulation result into an ArcGIS and a webpage platform to realize the real-time dynamic visual display of the simulation result. According to the invention, the pollutant concentration distribution and the dynamic change conditions at different moments and different spatial positions can be visually and intuitively displayed, an image and visual presentation platform is provided for the emergency disposal, and the emergency decision making can be effectively assisted.

The invention belongs to the technical field of smart robots and particularly relates to a smart accompanying robot for student learning in order to solve the technical problems that an existing smartaccompanying robot for student learning has the single function, can only conduct human-computer interaction and does not have the good learning assisting capability. According to the following provided scheme, the smart accompanying robot for student learning comprises a main base; the two sides of the bottom of the main base is connected with power crawler belts through bolts; a cleaning hole is formed in the position, located between the two power crawler belts, of the bottom of the main base; and a mounting plate arranged horizontally is connected to the position, located on the top of the cleaning hole, of the inner walls of the two ends of the main base through bolts. According to the smart accompanying robot for student learning, a pair of VR glasses are mounted in an egg chamber;a child can be put in the egg chamber and wear the VR glasses so that the child can receive more visual and stereoscopic education; the smart accompanying robot can more effectively assist the child in three-dimensional thinking education through VR education and can more effectively promote brain development of the child.

The invention provides a method and a device for acquiring a characteristic curve of a rod-pumped well underground system. The method includes: using an underground lifting system below a polished rod as a whole, and giving parameters of the rod-pumped well underground system; acquiring the characteristic curve of a pump inlet and outlet pressure difference related to actual displacement of a pump, according to the parameters of the rod-pumped well underground system; further, acquiring a characteristic curve of the pump inlet and outlet pressure difference related to power of the rod-pumped well underground system and acquiring a characteristic curve of the pump inlet and outlet pressure difference related to efficiency of the rod-pumped well underground system.

The invention discloses an Alzheimer's disease classification method and system based on an anatomical landmark and a residual network, and the method comprises the steps: carrying out the tissue segmentation modulation of a training image set, and obtaining a gray matter image; comparing voxels of the Alzheimer's disease image and the normal subject image in the training image set to identify ananatomical landmark; taking the obtained anatomical landmark as a center, and extracting grey matter blocks of the gray image; and connecting the grey matter blocks, inputting the obtained synthetic blocks into a residual error network model for feature extraction, taking features extracted by the residual error network model as input of a classifier, and classifying Alzheimer's disease patients and normal subjects in the test image set. The anatomical landmark is taken as the center, feature blocks of gray matters in three tissues of the brain are taken as the input of the residual network, the feature blocks are taken as the feature expression of each MR image, the residual network model is adopted to enhance the feature learning capability of the network, and the classification accuracyis enhanced.