18results about How to "Easy to dig" patented technology

The application provides a false news detection method and device based on reader behavior simulation. The method comprises: obtaining a news to be detected and extracting components; inputting the components into a trained false news detection model, the false news detection model comprising: two or more component-in-component feature extractors corresponding to the components one by one; a component-inter-component feature serialization module comprising one or more component-inter-component feature extractors and one sequence-based aggregator, the one or more component-inter-component feature extractors capturing component-inter-component features between any two components, and the sequence-based aggregator integrating all the component-inter-component features into a feature sequence according to a set order; and a detector obtaining true and false prediction probabilities. The false news detection model can discover the affinity between different components, comprehensively and effectively model the news, better mine the features within the components and between the components, learn better news representations by simulating the reading and verification behaviors of readers in the components, and improve the detection accuracy.

The application belongs to the technical field of information security, and discloses an attribute correlation-based differential privacy anonymous method. First, the correlation between attributes is analyzed through data distribution analysis of a data set, the number of each equivalent group of each attribute group is calculated by using permutation and combination, all minimum attribute combinations are found, if the number of each equivalent group of the attribute combination is greater than or equal to 30, and there is an equivalent group with a number less than 30 in each equivalent group when any attribute is added, the attribute combination is a minimum equivalent group. Then, the set condition of each attribute is obtained by performing intersection on all minimum attribute groups, the number of each attribute under the intersection is calculated, then the priority of the attributes with intersection is divided, the intersection number is used as the privacy protection priority of the attribute, privacy budget is allocated through the privacy protection priority of each attribute, and finally, the attributes with intersection are protected by differential privacy.

The utility model relates to a power supply line troubleshooting auxiliary device, which comprises a motor, a storage shell and a supporting column, and is characterized in that a rotating shaft at the output end of the motor is provided with a rotating rod; the storage shell is of a hollow structure with one open end, and the motor is detachably connected into the storage shell. The assembly shell is of a hollow structure with two open ends, and the storage shell is slidably mounted in the assembly shell; the supporting columns are arranged on the two sides of the assembling shell and movably connected with the assembling shell, and moving parts or inserting installation parts are installed at the bottoms of the supporting columns. By means of the assembling performance of the storage shell and the assembling shell and the detachable connection performance of the motor and the storage shell, the device can be transported in a separated mode, so that different technicians can carry separated parts, the problems that when the whole device is singly carried, the weight is too large, and the size is too large are solved, and the technicians can conveniently carry the device to excavate soil on a line. The device can quickly remove soil around the line, can reduce manpower output, and has good flexibility and practicability.

The application discloses a domain name resolution method and device based on domain name request risk management and control, the method comprises the following steps: identifying domain name requests as normal domain name requests or abnormal domain name requests; according to the user domain name access behavior data set and the abnormal domain name association strength, evaluating the security rating and the security score of the user; sending the normal domain name requests initiated by users with different security ratings to the DNS server subset cluster corresponding to their levels, so that the DNS server subset cluster of the level responds to the normal domain name requests in order based on the security score; predicting the normal domain names with high probability of access to form a domain name resource list, which is used to cache the domain name resource list to the selected DNS server when the security rating of the user is higher than the set threshold, so as to improve the domain name resolution cache hit rate and the resolution efficiency. The application solves the problem of reduced performance of the domain name server caused by the low utilization rate of the conventional DNS server due to the zombie network attack.

The invention discloses Chinese yam automatic digging equipment which comprises a digging machine body, a digging part and a cleaning part. The digging part is rotationally arranged at the front end of a digging arm of the digging machine body and comprises a digging shovel and a pushing oil cylinder, a pushing plate capable of moving left and right along the digging shovel is arranged in the digging shovel, and the pushing oil cylinder is arranged on the digging shovel and connected with the pushing plate; the cleaning part is connected with the rear end of the excavator body through a connecting frame and comprises a supporting frame and cleaning rollers, one end of the supporting frame is fixedly connected with the connecting frame, the multiple cleaning rollers rotationally connected with the supporting frame are evenly arranged on the inner side of the supporting frame in the extending direction of the supporting frame, chain wheels are arranged at the two ends of each cleaning roller, and the chain wheels located on the two sides of the supporting frame are connected in a staggered mode through chains. The chain wheel close to the excavator body is connected with a hydraulic part of the excavator body, damping supporting legs are arranged on the two sides of the rear end of the supporting frame, walking wheels are arranged at the bottoms of the damping supporting legs, and a discharging plate which is obliquely arranged downwards is arranged at the tail end of the supporting frame; and the baffles are obliquely arranged on the two sides in the supporting frame.

The invention provides an intelligent medical illusion detection method and system based on multi-modal data enhancement, and relates to the technical field of medical illusion detection. The method comprises the steps of collecting multi-modal medical data, and constructing an original multi-modal data set; performing data preprocessing on the original multi-modal data set, and generating a plurality of enhanced modal samples through semantic alignment and information fusion among modals by adopting a cross-modal data enhancement technology; modal feature vectors of the modal samples are extracted; according to the modal feature vector, determining a multi-modal consistency index; fusing the modal feature vectors, and determining an abnormal score; obtaining a semantic distance between the modal sample and a knowledge graph; determining illusion confidence; and according to the illusion confidence, judging whether medical illusion appears or not. According to the method and the device, the illusion content in the medical data can be detected according to the consistency of the multi-modal data, the abnormal score and the semantic distance between the multi-modal data and the knowledge graph, and the accuracy and the reliability of the medical data are improved.

The application discloses a kind of scientific research data analysis platform for fast radio burst, including data management module: for the structured, standardized, standardization management fast radio burst related scientific research data;Fast radio burst searching module: for searching fast radio burst in radio telescope observation data, and intercept fast radio burst sample storage in database;Fast radio burst sample analysis module: based on astronomical data analysis algorithm component, fast radio burst sample is in-depth analyzed, and analysis result is transmitted to visual module;Visual module: based on real galaxy distribution constructs 3D celestial sphere model, and fast radio burst data and analysis result are shown on the corresponding position of celestial sphere model.The application provides fast radio burst data acquisition, management and sharing function, constructs rich standardization data analysis capability, realizes analysis result visualization, greatly improves data acquisition and analysis efficiency, promotes astronomical achievement sharing, accelerates scientific research achievement output.

The utility model provides a flip sealing seasoning box, which comprises an upper cover, a sealing ring, a cover closing silica gel spring, a fixing pin and a box body, one end of the upper cover is provided with a first hinge part, the end of the box body corresponding to the upper cover is provided with a second hinge part, the first hinge part and the second hinge part are hinged through the fixing pin, and the sealing ring is arranged at the bottom of the upper cover. A hanging piece is arranged at the lower end, close to the second hinge part, of the box body; a cover closing silica gel spring penetrates through the upper cover and is hung on the hanging piece; when the upper cover is closed, the upper cover tightly presses the sealing ring through resilience force of the cover closing silica gel spring to enable the upper cover to be buckled on the box body in a sealing mode, and when the upper cover is opened and closed, the upper cover rotates to drive the cover closing silica gel spring to stretch around the fixing pin. The sealing ring is arranged on the upper cover of the flip sealing seasoning box, the cover closing silica gel spring is connected between the upper cover and the box body, through the combination of the sealing ring and the spring force, sealing and moisture prevention are achieved, seasoning is not caked, the quality guarantee period is long, meanwhile, the cover can be opened and closed through one-hand operation, and convenience and practicability are achieved.

This invention discloses a dynamically densely connected spatiotemporal feature decoupling network for recognizing cross-view gait, relating to the field of computer vision. It includes: an initial feature processing module, a dynamically dense spatiotemporal decoupling feature extraction module, and a feature enhancement processing module. The module uses dense spatiotemporal feature decoupling blocks and concatenation operations to achieve the sharing of shallow and deep network features, thereby addressing the problem of insufficient representation ability. Simultaneously, it employs an enhanced convolutional block attention mechanism to allow the network to focus on more important gait features. Finally, the feature enhancement processing module processes the five-dimensional feature mapping into multiple lateral features and performs batch standardization of the features to enhance representation ability and model generalization ability. This allows for the mining of correlations between shallow and deep features, alleviating the problem of insufficient information representation ability.

The application provides a text topic extraction method and device, computer equipment and a storage medium. The method comprises the following steps: obtaining a Bert word vector and a Bert sentence vector of a to-be-processed text; taking the Bert word vector and the Bert sentence vector as nodes to construct a topological graph model; optimizing the nodes of the topological graph model by using a graph autoencoder with an attention mechanism to obtain multiple features of each node; and analyzing the multiple features by using a clustering algorithm to extract topic information of the to-be-processed text. The method can improve the accuracy of text topic extraction.

The invention provides a mine model generation method and device, electronic equipment, a storage medium and a computer program, and the method comprises the steps: obtaining an initial OSGB model of a mine: drawing a polygon on the obtained OSGB model, and dividing the model into an internal region and an external region through the polygon; the polygon, the bottom face and a plurality of planes formed by projection lines between the polygon and the bottom face form an excavation body in a surrounding mode, and the excavation body is written into the initial OSGB model file. The generated excavation body does not damage the original osgb hierarchical association, and the excavation body can automatically generate the side wall in the osgb internal model, so that the defects of low efficiency and insufficient stability caused by the need of using an artificial area to carry out local excavation after a mine model is obtained in the prior art are overcome, and the mining efficiency is improved. The obtained excavation body model and the original osgb model can coexist in a structural body, so that excavation processing is repeatedly carried out on the osgb original model obtained through one-time collection.

The application discloses a kind of ground cover classification model training method, ground cover classification method and device, the ground cover classification model training method includes: obtaining training set;Sample image is input into ground cover classification initial model and is extracted to obtain feature image;First feature is obtained by carrying out first type feature processing to feature image, and first classification result is predicted using first feature;Second feature is obtained by carrying out second type feature processing to feature image, and third feature is obtained by extracting the deep feature of first feature, second feature and third feature are fused, and second classification result is predicted using the feature after fusion;Total loss of first classification result and second classification result is calculated using annotation information and is carried out back propagation, to adjust the parameters of ground cover classification initial model.By the above mode, the multilevel feature of high-resolution remote sensing image can be fully utilized, and the ground cover classification accuracy is improved.

This utility model discloses a planting device for transplanting camellia seedlings, belonging to the field of seedling transplanting. It includes a transplanting cover with a groove on its upper surface. A digging mechanism is inserted into the groove, and multiple digging mechanisms are arranged in a circular array. Each digging mechanism includes a telescopic plate, the outer surface of which is inserted into the groove. A rotating component A is fixedly connected to one side of the bottom of the telescopic plate, and a shovel plate is fixedly connected to one end of the rotating component A. An adjustment mechanism is fixedly connected to the other side of the bottom of the telescopic plate. Through the coordinated use of these devices, when transplanting camellia seedlings, the telescopic plate and shovel plate in the digging mechanism are directly inserted into the soil. After insertion, the shovel plate is folded so that it is perpendicular to the telescopic plate, facilitating the removal of soil from the bottom of the camellia seedling, reducing damage to the roots and stems, and avoiding affecting the growth of the seedling.

A method for preparing a binary formula for Dai pottery clay and its application is disclosed. The method involves taking Dai pottery clay from the Honghe River basin, five-colored clay from Honghe County, and charcoal powder. The Dai pottery clay and five-colored clay are sun-dried and weathered for at least three months. The Dai pottery clay from the Honghe River basin has a SiO2 content of not less than 50%, an Al2O3 content of not less than 15%, an Fe2O3 content of not less than 10%, and a loss on ignition of less than 10%. The five-colored clay from Honghe County has a SiO2 content of 72-82%, an Al2O3 content of 9-12%, and an Fe2O3 content of 3-5%. The method involves soaking the Dai pottery clay and five-colored clay in water until fully saturated, then ball-milling them. The slurry is sieved, and then charcoal powder is added. After stirring evenly, the clay is pressed to drain water and then kneaded to remove air. This invention can improve the throwing and molding performance of Dai pottery clay, increase the sintering temperature and the density and strength of its structure, and reduce the burn-off rate.

The utility model discloses a silt cleaning device for channel improvement, which relates to the technical field of channel silt cleaning equipment and comprises a crawler, a loading frame is mounted at one end of the crawler, a leak hole is formed in the inner side of a collecting barrel, an output shaft of a first motor is connected with one end of an auger, and the other end of the auger is connected with a second motor. The sludge collecting device is reasonable in design structure, the crawler, the collecting barrel, the auger, the rotary drum and the buckets are matched with one another, power can be provided for moving positions of carried parts through the crawler, sludge is dug through the buckets, the conveying pipe is connected with the conveying pipe, the conveying pipe is connected with the conveying pipe, and the conveying pipe is connected with the conveying pipe. The sludge collecting device has the advantages that the crawler, the collecting barrel, the auger, the rotary drum and the buckets are matched with one another to provide power for the moving positions of the carried parts; the dredger is simple in structure and convenient to use, excavated sludge is collected through the collecting barrel, power is provided for the sludge moving position through the auger, the purpose of cleaning the sludge in a river channel can be achieved, the problem that a grab bucket type dredger and a chain bucket type dredger are high in use cost is solved, and meanwhile manpower output is reduced.

The application relates to an industrial process fault diagnosis method, and discloses an industrial process fault diagnosis method based on a graph convolution network of space-time fusion, which comprises the following specific process: collecting fault data in an industrial production process, then performing z-score standardization processing and sliding window interception on the fault data to obtain a node feature matrix, and inputting the node feature matrix into a ST-Res-GCN model which has been trained and tested to obtain a fault classification result; the application proposes an industrial process fault diagnosis model based on a graph convolution network of space-time fusion, which can automatically acquire and deeply mine space-time fusion features in data, and effectively improves the fault diagnosis rate.

The application discloses a kind of for building construction foundation pit excavation and setting up of muck transport excavation equipment, and the top of excavator vehicle body is equipped with excavator muck bucket.By installing excavator muck bucket, excavator muck bucket can support roof stably, and staff need to make second motor rotate excavator mechanical arm by output through rotating disc, so that excavator bucket rotates to appropriate position with rotating disc as center, and then control excavator bucket to move like human wrist and arm, so that excavator bucket can excavate building foundation pit, and after excavator bucket excavates muck, staff need to control second motor to rotate rotating disc, so that excavator mechanical arm can move excavated muck to the position corresponding to excavator muck bucket, control excavator mechanical arm to move excavator bucket, so that excavator bucket discharges muck excavated in its inside to the inside of excavator muck bucket for storage and transportation, so that the device can excavate foundation pit conveniently under the premise of transporting muck, realize one machine multiple use and improve flexibility.

The utility model provides a servo supporting device for a circular foundation pit, which comprises a plurality of arc supporting beams which are arc section profile steel and form a supporting circular ring, and the supporting circular ring is positioned on the inner side of a circular diaphragm wall; the multiple hydraulic connector boxes are correspondingly arranged at the joints of the adjacent arc supporting beams, and each hydraulic connector box is correspondingly connected with the arc supporting beams on the two sides; the gap liner layer is arranged between the supporting circular ring and the circular diaphragm wall; and the hydraulic pump station is connected with the hydraulic joint box. The servo supporting device for the circular foundation pit can provide stable and reliable support for the circular foundation pit, and has the advantages of being short in construction period, easy to disassemble and the like.