68results about How to "Improve information utilization" patented technology

The invention relates to an ultrasonic image intelligent segmentation method based on the automatic context and data enhancement. The method comprises steps that firstly, a series of image pre-processing is carried out for an ultrasonic image data set to acquire a data set after pre-processing; secondly, data enhancement for the data set after pre-processing is carried out, and the data set scaleis expanded to acquire an amplified data set; thirdly, the amplified data set is inputted to the convolutional neural network based on the automatic context, a model is trained in an end-to-end mode,and preliminary segmentation of the amplified data set is realized; and lastly, refinement post-processing on the preliminary segmentation result is carried out. The method has advantages of high segmentation accuracy, strong robustness and generalization and good segmentation edge smoothness, and the ideal segmentation effect can be acquired under the condition of limited training data sets.

The invention discloses a wheel spoke type fault-tolerant six-dimension force sensor with a parallel structure, which is characterized in that the sensor is an inner and outer ring structure, more than six detection branches (3) are installed between a clamping ring (1) and a force measuring ring (4), a foil gauge is attached to the middle part of each detection branch, and both ends of the detection branch (3) are connected with the clamping ring (1) and the force measuring ring (4) through an elastic spherical hinge (2). The sensor with the parallel sensor is provided with more than six detection branches and has fault tolerant capability. The sensor is an integral structure, has simple structure and simple and convenient measurement principle and can be applied to various occasions requiring high-reliability six-dimension force measurement, such as robots, aerospace field, automobile wheel force measurement and the like.

The invention discloses a multi-hierarchy relationship information management system based on cloud computing. The multi-hierarchy relationship information management system based on the cloud computing comprises a cloud service platform and a client. The cloud service platform comprises a physical resource layer used for storing information data of all organization hierarchy units, a processing platform layer used for processing the information data on the physical resource layer, a displaying application layer used for displaying the information data and a management layer used for managing and maintaining the physical resource layer, the processing platform layer and the displaying application layer. According to the multi-hierarchy relationship information management system based on the cloud computing, a mode of one longitudinal layer and three transverse layers is provided and used for supporting the whole multi-hierarchy organization structure, and the whole system is made to meet requirements for 'one base, one platform, and one network' due to the fact that the multi-hierarchy relationship information management system based on the cloud computing is established. In addition, rich cloud computing abilities and a friendly user interface are provided, and the purpose that mass information is obtained from the interior of an organization, applied to the interior of the organization and analyzed by the interior of the organization is achieved. Therefore, safety performance and the information sharing rate of the system are improved, resources are utilized efficiently, and requirements that information is more integrated, supervision is more strict and decision-making is more convenient are met.

The invention relates to the technical field of user behavior trace mining, in particular to a user behavior similarity mining method based on the space-time mode. The space-time mode matching method of a sign-in point set is designed to carry out user behavior mining on data in consideration of the condition that sign-in records of LBSN users are discontinuous and seriously fragmented; sign-in points are classified into a sequence subset and isolated points, and time sequence information in the sequence subset is reserved and effectively integrated with position information in the similarity comparison process. By means of the new space-time Hausdorff distance matching method, space-time mode similarity discrimination can be effectively carried out, behavior trace recovery of the sign-in points is not needed, the sign-in time sequence information is effectively utilized, and therefore the similarity of user sign-in behaviors can be well judged.

Disclosed are a business information push service system and method. The business information push service system is composed of a mobile terminal application program, a merchant AP hotspot and a head dispatch server. A C / S transmission model based on GPS location is used for achieving push of business service information, and at the same time, further achieving a double-layer transmission model, namely, a head dispatch server- merchant AP hot-spot type and a merchant AP hotspot-mobile terminal type, for meeting the condition that a GPS signal is week. The mobile terminal application program can be installed in mobile devices, such as mobile phones and palm computers, capable of being accessed into internet and enabling the GPS to be used, and therefore the business service information which is screened can be automatically pushed to a user which enters a merchant.

The present invention discloses a storing method of communication record, a display method and a communication terminal thereof. The storing method comprises the following steps: obtaining grouping information of communication peer end which communicates with the communication terminal; generating the communication record comprising the grouping information; and storing the communication record to a grouping space which is established beforehand and is corresponding with the grouping information. As the invention stores and displays the communication record according to grouping information, the information usage factor of communication record is increased. When the communication record of a specified user needs searching, the item-by-item searching is not required. The positioning to a corresponding grouping is executed. The management of communication record is facilitated. Furthermore the availability and user experience of mobile terminal are increased.

The invention discloses a fault-tolerant wide-range parallel six-axis force sensor, which mainly comprises an outer fixing ring, an inner proving ring, more than six detection branches and three or four bearing branches, wherein an annular polyhedron is formed by enveloping the inner proving ring and the outer fixing ring with a plane which is vertical to a branch axis; the inner surface of the inner proving ring is provided with a screw thread; the upper surface of the outer fixing ring is provided with a plurality of through holes, and can be connected with the outside through a bolt; the bearing branches are high-stiffness beams; the two ends of the high-stiffness beams are fixedly connected with the outer side of inner proving ring and the inner side of the outer fixing ring respectively; the detection branches are arranged pairwise among the bearing branches; the two ends of the detection branches are connected with the outer side of the inner proving ring and the inner side of the outer fixing ring through elastic spherical hinges; and a strain foil is attached to the middle part of each detection branch. The sensor can have an integral or assembled structure. The fault-tolerant wide-range parallel six-axis force sensor is reliable in structure, has high rigidity, a wide range and fault tolerance performance, and can be widely applied to the six-axis force measuring environment of a plurality of sensors requiring wide ranges and high reliability such as six-axis force measurement of aerospace, military, nuclear industry, robots, automobiles and the like.

The invention discloses an intelligent highway warning trolley, belongs to the field of highway information processing, and relates to a road condition information prompting device. The intelligent highway warning trolley comprises a warning board, a camera, a wireless communication module, a chassis, a motor, a visible light luminance sensor, a motor driving module, a central processing module, a gray level sensor, wheels, a power source, a warning board fixing support, a stretching support, a pyroelectric infrared sensor and a hand-held terminal. The warning board is fixed to the front portion of the chassis through the warning board fixing support, and the camera is fixed to the front portion of the chassis in the mode of being tightly attached to the warning board. The wireless communication module is fixed to the back middle portion of the chassis in the mode of being tightly attached to the central processing module through a supporting column. By means of the intelligent highway warning trolley, warning marks can be carried on highways in all levels, the road conditions can be monitored and fed back in real time, and the intelligent highway warning trolley can automatically walk to the preset position. The hand-held terminal is controlled through wireless communication, has the hand-held control mode and the automatic control mode, and free switching is achieved.

The invention belongs to the technical field of water treatment and discloses a water purification plant intelligent chemical adding control system and method based on digital twinning. The method comprises steps that digital twins of a dosing room is established; real-time monitoring data in the operation process of the physical dosing room is acquired through data acquisition equipment, and is transmitted to the management platform through the network transmission system; the management platform transmits the real-time monitoring data to the digital twins of the dosing room through the network transmission system; the digital twins of the dosing room dynamically map the production condition of the physical dosing room; three-dimensional visual monitoring and display on the digital twinborn body in the dosing room are carried out through a three-dimensional visual system; the management platform predicts the dosage by using an LSTM neural network based on the real-time monitoring data to obtain the dosage prediction information, and obtains the adjustment control information according to the dosage prediction information and the real-time monitoring data; and the physical dosing room adjusts the dosing amount according to the adjustment control information. The method is advantaged in that a problem of serious waste of a flocculation dosing mode in a water plant can be solved.

The invention discloses a music recommendation method and system based on a knowledge graph, belongs to the field of knowledge graphs and content recommendation, and aims to solve the technical problem of how to improve the accuracy of music recommendation by using context information in auxiliary information. According to the technical scheme, the method specifically comprises the following steps: constructing a music recommendation knowledge graph: constructing the music recommendation knowledge graph by utilizing an original music data set, obtaining potential interests of a user, and stimulating the propagation of user preferences on a music knowledge entity set according to the potential interests; constructing an ST_RippleNet model: constructing the ST_RippleNet model by integrating various source heterogeneous data in the music recommendation knowledge graph, introducing a low-dimensional vector and adopting a triple multilayer attention mechanism, so as to make full use of knowledge information of the music recommendation knowledge graph; carrying out model optimization, wherein an RMSProp optimizer is used for carrying out optimization on the ST_RippleNet model; and constructing a loss function of the ST_RippleNet model, wherein the loss function is improved, and the loss of the ST_RippleNet model in the recommendation process is reduced.

The invention discloses a part and system test based reliability evaluation method for an automobile automatic gearbox, and belongs to the technical field of automobile automatic gearbox research. The method comprises: performing part reliability evaluation according to test data of parts such as a hydraulic torque converter, an electro-hydraulic operation apparatus, a gear speed change mechanism, a gear shifting clutch and the like in the automobile automatic gearbox, and obtaining reliability prior information of a system according to a serial model; performing reliability evaluation according to system-level test data to obtain reliability field information of the system; and further, performing Bayesian data fusion on the prior information and the field information to realize part and system test based reliability comprehensive evaluation of the automobile automatic gearbox. According to the method, the reliability evaluation of the automobile automatic gearbox can be performed by utilizing test information of the parts and the system, and the characteristics of reliability problems of mechanical parts can be reflected, so that an evaluation result is relatively high in credibility and the information utilization rate is high.

The invention discloses a parallel type genetic Elman neural network-based source driving 235U concentration recognition method, which mainly comprises the following steps: establishing a neural network model, wherein the neural network model is structurally divided into three layers which are a data allocation layer, a sub-network layer and a comprehensive decision-making layer respectively; preprocessing an acquired neutron pulse signal auto-correlation function; inputting a processed signal auto-correlation function sample into the data allocation layer of a parallel type genetic Elman network and adopting a cyclic random multi-point sampling method to allocate the data of the sample; inputting the allocated data into each genetic Elman sub-network in the sub-network layer respectivelyfor recognition and giving recognition results; and performing comprehensive processing on the recognition results of the plurality of sub-networks by the comprehensive decision-making layer to obtain a final 235U concentration recognition result. Through the method, relatively better 235U concentration recognition effect is obtained due to relatively higher data utilization ratio and a novel network structure.

The invention discloses a disaster cellular alarm linkage system based on interval argumentation multi-sensor fusion of particle swarm optimization. The system comprises a fire monitoring alarm linkage system, a public fire alarm system and a property management platform, and is characterized in that the fire monitoring alarm linkage system comprises access control terminals of building doors of all units of a community and cellular user terminals, and emergency alarm switches are arranged on both a real estate management platform and the fire monitoring alarm linkage system; the public fire alarm system comprises a CO sensor, a smoke sensor, a temperature sensor and an alarm controller which are arranged in a resident of a community, and a fire judgment data fusion algorithm based on IPSO optimization interval demonstration multi-sensor fusion is arranged in the alarm controller. According to the present invention, the fire monitoring and alarming linkage system is matched with the public fire alarming system to work, the automatic fire alarming and the manual fire alarming are integrated, and the uncertainty of the sensor measurement data is eliminated based on the fire judgment data fusion algorithm based on IPSO optimization interval demonstration multi-sensor fusion.

The invention provides a method and device for searching movie information and relates to the technical field of Internet. The method comprises following steps: obtaining searching data; matching the searching data with movie theater data, movie data and movie actor data in a database; sending information corresponding to the matched data to a user terminal according to the matching results, wherein the matched data comprises at least one of the movie theater data, movie data and movie actor data which are matched with the searching data. According to the scheme provided in the embodiment of the invention, the movie theater data, movie data and movie actor data in the database are matched with searching data so that the searching data is not limited to certain input data; users can obtain corresponding matched results only if inputting data relevant to a movie.

The invention discloses a system notice transmitting method, device and system and belongs to the field of communication. The method includes the steps that a coalesced billing system (CBS) generates a system notice, the CBS obtains a notice type of the system notice, the CBS judges whether the notice type is a preset notice type, and when the notice type is the preset notice type, the CBS sends a system notice to a marketing system; the marketing system adds marketing information to the system notice; the marketing system sends the processed system notice to a user device. By means of the system notice transmitting method, device and system, the problem that the information utilization rate of the system notice is low is solved, the information utilization rate of the system notice is improved and the system notice transmitting method, device and system are used for sending the system notice.

The invention discloses an anti-air intercepting aircraft guidance method based on speed control and belongs to the guidance law research field of anti-air intercepting aircrafts. Step 1, the motion position of a target is predicted according to Kalman filtering; step 2, the encountering point position of an aircraft and the target is designed; step 3, the speed, launch time and the emission angle are calculated according to the encountering point position designed in the step 2; step 4, after the aircraft is launched, if the motion state of the target is changed, whether the position of the encountering point is updated or not needs to judged; and step 5, finally, the aircraft encounters with the target in the encountering point position. With the anti-air intercepting aircraft guidance method based on speed control, the moving direction and speed of the target are controlled, and finally the target is accurately targeted by means of the target motion predication technology and the encountering point design technology.

The invention discloses a graph model based on multi-view dictionary learning. The method comprises the steps: carrying out the data dimension reduction and preprocessing of original graph data through principal component analysis and linear discrimination analysis, removing redundant features in the data, and maintaining the high discrimination of the data; learning essential characteristics contained in the data by using a multi-view dictionary learning method, and training to obtain a comprehensive dictionary, an analysis dictionary, sparse codes corresponding to the samples and an SVM linear classifier; inputting the sparse codes of the samples into an SVM classifier, and generating a plurality of prediction labels under different visual angles according to a multi-visual-angle principle after the sparse codes are processed by the classifier; the predicted multi-view labels are integrated through a voting mechanism, and final sample labels are generated and used for calculating model accuracy; the method has the advantages of high information utilization rate, more efficient decision making, high specificity and the like.

The invention discloses a method for analyzing clinical data in wards, including: collecting information, integrating and processing information, integrating and classifying the collected information, classifying basic medical care problems from patient terminals, and assigning them to different departments, and then displaying On the doctor terminal and the nurse terminal; extract information, and integrate the extracted data, and then extract the basic information; merge the integrated information and the extracted basic information, and store the merged information in the database; Whether the patient terminal sends a query request to the system, if yes, analyze the content of the requested information, and then send the content of the requested information to the database, and retrieve relevant information from the database, if not, end; whether the patient terminal has the ability to generate a report Request, if yes, generate report, and download or print, if otherwise end. Improve the accuracy of recommendations and improve the efficiency and quality of clinical information utilization.

The embodiment of the invention discloses an information sorting method and device, electronic equipment and a computer readable medium. The method comprises the steps of obtaining a candidate information set for a target user; extracting feature information corresponding to each part of candidate information in the candidate information set; respectively inputting each part of feature informationinto a pre-trained sorting model, obtaining the score of each part of candidate information; wherein the sorting model comprises a multi-task network and a fusion network, the multi-task network comprises a plurality of sub-task networks with dependency, the different sub-task networks are used for predicting the probability of occurrence of different user behaviors, and the fusion network is connected with the sub-task networks and used for predicting scores of candidate information based on the probability predicted by the sub-task networks; and sorting the candidate information based on the scores. According to the embodiment, the accuracy of the information sorting result is improved.

The invention discloses a load identification and multi-sensor fusion sensing method and device, and belongs to the technical field of power monitoring, and the method comprises a power monitoring unit which is used for installing one or more intelligent sensors on an existing power grid to carry out the monitoring and collection of current and voltage; information processing: processing the acquired information by using algorithms of different theories; in the sensing fusion process, complete information about electric power is obtained by using a plurality of sensors, and the survival ability of an electric power system is enhanced in the aspects of detection, tracking and electric power identification by using a multi-sensor data fusion technology. Through reasonable control and use of multiple sensors and observation information thereof, redundant or complementary information of the multiple sensors in space or time is combined according to a certain criterion so as to obtain consistent explanation or description of a tested object, data is processed based on NILM, decomposition and analysis of a power grid can be realized, and the reliability of the power grid is improved. And the limitation when load identification is carried out by using the load steady state characteristic information can be overcome to a certain extent.

The invention provides a characterization method of similarity between polarized synthetic aperture radar images, belonging to the radar image processing technology field. The method comprises the following steps: in a plurality of multi-polarization SAR images whose similarity is to be characterized, calculating a coherent coefficient gamma13 between an HH channel and a VV channel of all pixel points (x, y) of each multi-polarization SAR image, and obtaining a coherent graph gamma corresponding to each multi-polarization SAR image; calculating a similarity MI (gamma A, gamma B) based on mutual information between any two images in the plurality of multi-polarization SAR images whose similarity is to be characterized, wherein MI (gamma A, gamma B)=H(gamma A)+ H(gamma B)-H(gamma A, gamma B). According to the invention, a coherent coefficient between copolarization channels is utilized to carry out similarity characterization, and utilization rate of image information is raised; when estimating a coherent coefficient between polarized channels, not only is information of center pixel is utilized, but also polarized information of a surrounding pixel is utilized, and robustness of the coherent coefficient is raised; mutual information measure with good anti-noise performance and acutance characteristic is employed carry a coefficient information source so that the similarity characterization is carried out; thereby a base is established for subsequent accurate efficient multipolarization SAR image rectification.

The embodiment of the invention provides a multimedia processing method and device and a server. The method comprises the steps: when a multimedia information issuing request is received, obtaining multimedia information requested to be issued; detecting whether the multimedia information contains watermark information or not; if the multimedia information contains the watermark information, searching preset topic information for topic information matched with the watermark information; issuing the multimedia information, and issuing the topic information matched with the watermark information. According to the multimedia processing method, the information utilization rate of the watermark information can be improved, the topic information issuing mode is expanded, and the intelligence is improved.

The invention discloses an entity relationship graph construction method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the steps of extracting relationships between entities and creating an entity relationship library; displaying an entity relationship graph in a single view according to the entity relationship library; and / or displayingan entity relationship graph in a panoramic view according to the entity relationship library, wherein the entity relationship graph comprises entities and relationships between the entities. According to the embodiment, the problems of dispersed maker entity informatio, lack of maker relationship focusing, a single maker relationship display form, and lack of intelligent recommendation is solved, and the efficiency of maker management is improved.

The invention belongs to the technical field of industrial process control, and particularly relates to a non-ferrous metallurgy unit process digitization and modeling method based on the process state space. The method comprises the steps that S1, high-dimensional process parameters related to dynamic characteristics of a non-ferrous metallurgy overall process are obtained and divided into controlled variables, inlet conditions and reaction conditions, encoding is conducted, and the process state space is established; s2, low-dimensional depth features are extracted from the high-dimensionalprocess parameters, and the process state space is divided into subspaces for different working conditions according to the variance of the depth features; s3, under a process state space framework, the unit process dynamic characteristics of the subspace are expressed as the sum of a nominal term and a deviation term, and the deviation term is introduced by regression of low-dimensional depth characteristics; s4, according to the positions of the unit processes in the process state space, the probabilities of the unit processes belonging to different working conditions serve as weights, the unit process models under the different working conditions are weighted, and a real-time dynamic model is obtained. The method is high in modeling precision and high in information utilization rate.

The invention discloses a method for synchronizing identifying information and electronic equipment. The method applied to the electronic equipment includes: acquiring first image identifying data of a first image; when a file data packet corresponding to the first image is determined to be the first image file data packet, acquiring the first position, for storing the first attached data of the first image, in the first image file data packet; writing the first image identifying data into the first position to form a second image file data packet so as to allow the first image identifying data to become one part of data in the second image file data packet. The method has the advantages that by writing the human face identifying result of the image into the attribute information of the image, the human face identifying result of the image is integrated with the image, the technical problem that the image identification result and the image are separated is solved, and information utilization rate is increased.

The invention discloses a mechanical system fault detection method based on broadband spectrum processing. The method comprises the following steps that S1, an acoustic sensor collects a voiceprint signal s(n) of the running state of a mechanical system; S2, noise suppression processing ss(n) is carried out on the acquired signal s(n); S3, delay acquisition is carried out on the normal state signal, and a normal state voiceprint library N_S(n) is formed through the step S2; S4, voiceprint matching is carried out on ss(n) based on N_S(n), in the matching case, a normal state voiceprint libraryN_S(n) is updated, and in the not matching case, a fault state voiceprint library and fault label editing are updated; and S5, if a fault is found, early warning prompt is carried out, the step S1 isreturned, and if no fault exists, the step S1 is returned. The method does not depend on priori knowledge of fault signals, the information utilization rate of the signals is high, the signal-to-noiseratio of the signals is improved, and the detection result is more accurate.

The invention discloses an ultraviolet light cooperation multi-sensor data fusion unmanned aerial vehicle friend or foe identification method, which comprises the following steps: dividing unmanned aerial vehicle target feature information obtained by a radar sensor, an ultraviolet light detection sensor and an ESM sensor into a training group and a test group, training a BP neural network through the training group, and verifying the correctness of the BP neural network through the test group; secondly, after unmanned aerial vehicle target feature information is input, enabling the BP neural network to automatically classify unmanned aerial vehicle target attributes, and using the IFF system and the BP neural network to obtain a target recognition probability; then, judging target attributes of the unmanned aerial vehicle by using a D-S evidence theory, and distributing corresponding weight values; finally, fusing the weight values obtained by the sensors and the IFF system, unifying friend or foe identification attributes, and obtaining an identification result. According to the method, the friend or foe identification is carried out by adopting multi-sensor data fusion, so that the obtained target information has higher resolution and reference, and a more accurate identification result is obtained.

The embodiment of the invention discloses a three-dimensional model monomerization method, device, electronic equipment and a readable medium. The method comprises the steps of obtaining a top view ofa three-dimensional model; carrying out semantic segmentation on the top view, and determining a target object to be subjected to monomerization based on a semantic segmentation result; obtaining a boundary line of the target object from the top view; and based on the boundary line, carrying out monomerization on the target object in the three-dimensional model. According to the embodiment, the information utilization rate in the three-dimensional model monomerization process is improved, so that the accuracy of three-dimensional model monomerization is improved.

The embodiment of the invention provides an information processing method and a device, which relate to the field of communication technology, and can determine the distribution density of a crowd through microblog data, and then carry out regional planning by referring to the distribution density of the crowd, thereby improving the information utilization rate of the microblog data and benefitingthe development of the information society. The method comprises the following steps: firstly, acquiring microblog data of a user in a designated area, wherein the microblog data at least comprises location information; Secondly, determining the population distribution density within the designated area based on the location information as a first reference index for planning the designated area.The technical proposal provided by the embodiment of the invention is applicable to the process of carrying out regional planning on towns.