67results about How to "Detailed classification" patented technology

The invention relates to a system and a method of detecting interference of a wireless signal based on spectral analysis. The system comprises a data acquisition unit, a data preprocessing unit, a feature extraction unit, a classification detection unit and a display unit, wherein the data acquisition unit is used for collecting the wireless signal in the environment, carrying out fast Fourier transform FFT on the collected wireless signal to obtain FFT data provided with frequency spectrum information, and transmitting the collected wireless signal to the data preprocessing unit; the data preprocessing unit is used for obtaining time domain information and the frequency spectrum from the collected wireless signal, and transmitting the time domain information and the frequency spectrum to the feature extraction unit; the feature extraction unit is used for carrying out feature extraction on the time domain information and the frequency spectrum which are obtained by the data preprocessing unit, and transmitting the extracted frequency spectrum features to a classification recognition unit; the classification detection unit is used for carrying out training and classification recognition on the frequency spectrum features extracted by the feature extraction unit, and transmitting a result obtained after training and classification recognition to the display unit; the display unit is used for providing an interactive interface for displaying a recognition result.

The invention discloses a motorcycle type identifying method in a complex scene, which comprises the following steps of: initializing a component dictionary of a video image, learning a parameter of each component in the component dictionary, calculating an optimal composition structure according to the learned parameters of the components and an XOR searching tree, training and integrating vehicle templates by adopting the optimal composition structure, and detecting and identifying a motorcycle type in the video image by using the vehicle templates. According to the motorcycle type identifying method, the optimal composition structure of the vehicle templates is learned by adopting a dynamic planning algorithm, the XOR searching tree and a large quantity of actual samples, thus the efficiency of training the templates is increased, better discrimination is achieved, and actual application is facilitated. According to the motorcycle type identifying method, by combining a Latent SVM (Support Vector Machine) algorithm and a robust HOG (Histograms of Oriented Gradients) characteristic, the motorcycle type in the complex scene can be processed, and instantaneity and generality are ensured.

A method for automatic classification separately collection and automatic transportation of the solid waste is designed to replace the manual door to door collection of the waste by the computer, and getting the waste for valuable recycle and reuse comprises of putting the waste into the automatic waste collectors set at the source of the waste producing and connected with pipeline, identifying the waste by the main board (21), classifying the waste by the selector (6), depositing the waste in the containers (1), (2) and (3), fluidizing the wastes by rolling fluidizing assembly (15), under the monitoring of the supervisory control center, separately transporting the wastes into the correspond waste recycle center, and getting the solid waste automation.

In an automatic defect classifying method, defects not reviewed are assigned with defect classes having the same definitions as those of reviewed defects in order to effectively use information on defects not reviewed, the defects not reviewed occupying most of defects on a wafer. Defects not reviewed are assigned defect classes having the same definitions, by using defect data of defects detected with an inspection equipment and defect classes of already reviewed defects given by ADC of a review equipment. Since all defects are assigned the defect classes having the same definitions, more detailed analysis is possible in estimating the generation reasons of defects.

The invention discloses a data management system based on river ecological monitoring. The data management system comprises an ecological monitoring and evaluating module, a data management platform and a forecasting and early warning module, wherein the ecological monitoring and evaluating module is used for evaluating monitored river monitoring data according to multiple evaluation indicators to obtain an ecological monitoring and evaluating result of a river, and the ecological monitoring and evaluating result comprises the health condition, existing problems and development trend of a river ecological system; the data management platform can be used for managing the monitored river monitoring data and taking the ecological monitoring and evaluating result as shared data to realize information sharing and communication; and the forecasting and early warning module is used for forecasting and early warning the river based on the river monitoring data and the ecological monitoring and evaluating result. The data management system can be used for accurately and comprehensively evaluating the repair or maintenance effect of the river ecological system, thus comprehensively judging the ecological regime of the river from multiple aspects, and forecasting and early warning different emergencies.

The invention discloses a method and a device for classifying short messages, a communication terminal and a server. The method comprises the following steps of carrying out word segmentation on a target short message to obtain at least one participle of the target short message; obtaining at least one word vector of at least one participle and generating a short message word vector of the target short message according to at least one word vector and a corpus word matrix; obtaining a subject vector to which the target short message belongs according to at least one participle; classifying the target short message according to at least one participle, the short message word vector and the subject vector to obtain a first type to which the target short message belongs. According to the method and the device for classifying the short messages, the communication terminal and the server, a technical problem of lower accuracy of a classification result, which is caused by classifying through the participle only, in the prior art is solved, and a technical effect of improving the accuracy of the classification result is realized.

The invention discloses a method and a device for sorting wood according to colors and wood grains. The method comprises the following steps of: establishing categorical data, collecting wood images, confirming wood categories, starting sorting devices, and the like. The device comprises a wood conveying belt, a wood video imaging device, a plurality of wood sorting devices and a program control system, wherein the video imaging device is arranged at the beginning end of the wood conveying belt, the plurality of wood sorting device are arranged at the lateral side of the wood conveying belt at the downstream of the video imaging device in an equidistance way, and the video imaging device and the plurality of wood sorting devices are respectively in circuit connection with the program control system. The invention has accurate sorting and high working efficiency and avoids the individual difference and the inconsistency of manual sorting.

The invention discloses a travel mode identification method based on big data machine learning, which comprises the following steps: extracting a training sample investigation object and dispatching an acceleration detection device; Collecting mobile phone signaling data and acceleration detection device data; Analyzing the data fluctuation characteristics, getting the velocity and acceleration fluctuation characteristic data as the forecast input value, travel mode as the output value; extracting 80% of that data from the input parameter set as the input data set, and adopting the corresponding travel mode set as the output set to train the machine learning algorithm, and the prediction accuracy of each algorithm is detected with the remaining 20% of the data; Machine algorithm training achieves more than 80% prediction accuracy, can be used to divide the travel mode, setting the input data set as the velocity acceleration characteristic data set, the algorithm output value is the travel mode. The travel mode identification method of the invention has the characteristics of small workload and high identification accuracy.

The invention belongs to the field of gold tailing treatment, and particularly relates to a method for fully utilizing gold tailings. The method mainly comprises the following steps that multi-elementtailings are subjected to swirler grading, are further screened through a sand washer, are further graded by a grader, and are screened after being dried to obtain fine sand with different levels; meanwhile, an overflow part with smaller specific gravity graded by the grader is dehydrated and precipitated through a high-efficiency thickener, then layer-by-layer screening is carried out through amulti-stage desliming hopper, finally dehydrating is carried out on the most fine overflow part by using a dewatering sieve to obtain silicon micropowder which is excellent in performance and is widely applied; and a bottom flow which is precipitated by the high-efficiency thickener can be stored in an air-inflation type slurry storage tank, and is used for producing an aerated brick. According tothe method, the multi-element tailing treatment method is more refined, the gold tailings can be thoroughly utilized, no harmful gas is emitted to the environment, the method can be applied to different fields and occasions, maximum utilization of the tailings can be achieved, and the method is the most environment-friendly and most economical tailing treatment method.

The invention provides a wallpaper display method. The wallpaper display method comprises extracting an image attribute parameter corresponding to the current wallpaper; searching a target wallpaper in a wallpaper library, wherein the difference between the image attribute parameter corresponding to the target wallpaper and the image attribute parameter corresponding to the current wallpaper is within a preset threshold scope; and displaying the target wallpaper in a wallpaper application. The wallpaper display device comprises a parameter extraction module, a wallpaper searching module and a wallpaper displaying module. According to the invention, by obtaining the image attribute parameter corresponding to the current wallpaper, the wallpaper type which the user likes can be obtained; by comparing the difference between the image attribute parameter corresponding to the target wallpaper and the image attribute parameter corresponding to the current wallpaper, the wallpapers are recommended; wallpapers can be classified more meticulously, wallpapers which the user likes can be recommended to the user, and the case that the user needs to screen wallpapers one by one when setting the wallpaper can be avoided.

The invention discloses a rice multi-stage screening device, which comprises a primary screening device and a secondary screening device. The primary screening device includes a primary screening box, a feeding hopper, an air blowing box, a blower, a second A material guide plate, a primary screen plate, a second material guide plate and a collection box; the secondary screening device includes a secondary screening box, a secondary screening mechanism, a first material storage box and a second material storage box, the secondary screening mechanism includes a first bearing block, a secondary screening rotor, a second bearing seat and a mechanism for driving the secondary screening The motor that rotates the drum. The first-stage screening device of the present invention uses air blowing and screening plates to initially screen rice, and handles rice bran and microparticles in the rice, which improves the efficiency of preliminary screening; Screening, and screen the whole rice and broken rice in the rice with the screening cylinder with through holes.

The invention discloses a tag recommendation method and system. The method comprises the following steps: obtaining a total tag set marked by all users on all projects; discovering the maximum frequent item set in the total tag set of the system by using the Apriori algorithm; setting the maximum frequent item set of the system as a new identifier; replacing the maximum frequent item set in the first tag set of the system with the new identifier of the system to form a second tag set; corresponding the users, the projects and the second tag set to generate user-project-tag three-dimensional tensor data, and setting an association weight of the three components as 1; decomposing the three-dimensional tensor data of the system by using the HOSVD algorithm to obtain the weight value of a tag marked by each user for each project; and recommending a tag with a high weight value to the first user, so that the user uses the tag to mark the project, wherein the user is the user who tags the project for the first time. By adoption of the method or system provided by the invention, the tag classification can be more precise, the accuracy of the recommendation system is improved, and the hit rate is gradually increased.

The invention discloses a high-resolution SAR (Synthetic Aperture Radar) image classification method based on intensity ratio and spatial structure feature extraction. The method comprises the following steps: performing mirror reflection on a classified SAR image around a boundary to perform boundary expansion; Carrying out block extraction on the extended SAR image; Calculating spatial structurecharacteristics of the block; Performing boundary expansion on the original SAR image again to extract blocks; Calculating an intensity ratio characteristic coefficient of the block; Carrying out vector superposition on the intensity ratio characteristics and the spatial structure information characteristics; Selecting a part of sample points and putting the sample points into an SVM classifier to train a model; And putting the whole image into the model to obtain a final prediction label image as a final classification result image. The method has the advantages that classification is finer,boundaries are more obvious, and region extraction features are easier to be classified, and can be used for SAR image classification and target recognition.

A method for restarting up information-recording includes judging whether information of this start-up is recording or not after unit is restarted up, recording information of this start-up if information of this start-up is not recorded in order to let maintenance personnel know more about operation state of unit and discover as well as solve problem timely.

The invention relates to a method for obtaining a universal security demand of embedded software. The method comprises the steps of obtaining static structure elements and dynamic running structure elements of the embedded software according to a static modeling mechanism and a dynamic modeling mechanism respectively; obtaining failure modes of the static structure elements and the dynamic runningstructure elements; setting security measures for the failure modes, and obtaining the universal security demand; and tailoring the universal security demand. According to the method, the comprehensiveness and expansibility of obtaining the universal demand of the embedded software can be effectively improved.

The invention discloses a medicine cabinet for improving medicine taking speed, comprising a cabinet body and a wall panel, characterized in that a convex plate is arranged on the top of the cabinet body, a ring track is arranged on the top of the convex plate, and a ring track is arranged on the top of the annular track. Leather pad, the bottom of the cabinet is provided with a moisture-proof chassis, the wall panel is provided with fixing ears and a first fixing pile, the bottom of the wall panel is provided with a rotating arm and a brush pad, the bottom end of the rotating arm is provided with a roller, and the medicine table It is connected with the first fixing pile through a telescopic rod, and the top of the medicine loading table is provided with a partition plate. In the present invention, a cylindrical cabinet is arranged to expand the storage capacity of medicines and improve the convenience of taking medicines. A rotatable wall panel is arranged above the cabinet to facilitate taking medicines faster. The invention has a simple structure and a reasonable design, and is suitable for Different medical care and medical facilities have shown significant advantages in various aspects.

The invention belongs to the technical field of biological information, and particularly relates to a mutation sequence annotation method, which comprises the following steps of: (1) determination ofmutation sequence information: obtaining a mutation sequence, integrating reference sequence information, and standardizing the mutation information; and (2) variation annotation, wherein the annotation result comprises an annotation function region, a variation type, a nucleic acid sequence and an amino acid sequence. According to the method, the existing function of the industrial gold standardANNOVAR can be realized, the defects in ANNOVAR are overcome, the aspects of distinguishing of splicing site and splicing region variation, CDS edge variation, annotation frameshift and stoposes/stopgain and the like are perfected, a normative expression mode is used, the gene number Entrez ID is also increased, and the method has good application value.

The invention is applicable to the field of home furnishing, and particularly relates to an intelligent high-rise storage cabinet. The cabinet comprises a lifting system additionally provided with a platform, and further comprises a moving system consisting of a transverse moving system, a longitudinal moving system and a vertical moving system; a pick-and-place structure is additionally arrangedon the moving system; the moving system and/or the lifting system are/is connected with a man-machine interaction control system. A set of complete intelligent household high-rise storage system is established, voice control is achieved through a voice control module, needed articles are obtained through cooperative movement of a transverse moving system, a longitudinal moving system and a vertical moving system and by means of a taking and placing structure, and searching of the two hands is liberated; meanwhile, the articles are carefully classified, so ; the convenience of article storage is improved; the cabinet is simple in structure, good in stability, good in accuracy and convenient to install, the upper space of a family is fully utilized, manual tedious operation is reduced, and the family space is simpler.

The embodiment of the invention discloses a guidance data sending method, a guidance data sending device, a terminal, a server and a storage medium, and belongs to the technical field of the Internet.The method comprises the steps of obtaining interface information of a current display interface of a terminal; obtaining current attribute information of the intelligent guidance equipment bound with the terminal; obtaining target guidance data matched with the interface information and the attribute information according to the first corresponding relation and the second corresponding relation,wherein the first corresponding relationship comprises a corresponding relationship between the interface information and the guidance data set, and the second corresponding relationship comprises acorresponding relationship between each piece of guidance data in the guidance data set and applicable attribute information; and sending the target guidance data to the intelligent guidance device, the intelligent guidance device playing the target guidance data, and the target guidance data being used for guiding the user to operate. In this way, the user can be flexibly guided in the operationprocess of the user. The obtained target guidance data is more consistent with the current scene, so that the user can be guided to operate better.

The invention discloses a radiology department image data storage method and system, which belongs to the technical field of image data processing and comprises an image data acquisition module, an image data classification module, an image data storage processing module, an access verification module and a control processing module. The image data acquisition module, the image data classification module, the image data storage processing module and the access verification module are all in communication connection with the control processing module. According to the invention, by arranging the image data acquisition module, image data of each image device can be conveniently acquired and subjected to noise reduction processing, so that a doctor can check and diagnose more conveniently; through the image data classification module, two-stage classification is carried out on the image data of each image device in a two-stage classification mode, classification is more detailed, and follow-up tracing is facilitated; and the image data storage processing module is arranged to encrypt the database, so that the security risk of the image data is greatly reduced, and the privacy of the patient is also protected to a certain extent.