Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

795results about How to "Add support" patented technology

Zero-trust access control method based on cloud side-end cooperation

The invention provides a zero-trust access control method based on cloud side-end collaboration, which comprises the following steps of: deploying zero-trust agents on application servers of cloud, side and end layers, and collecting multi-source trust measurement index data of each layer in real time; the method comprises the following steps: encrypting data, packaging the encrypted data into a standardized data packet, transmitting the standardized data packet to a security evaluation server through a security communication protocol, after the security evaluation server receives the encrypted data packet, carrying out refined multi-dimensional security evaluation in combination with an equipment identifier and network attributes, comprehensively considering various indexes through a weighting algorithm, and carrying out other operations. According to the invention, data transmission and control among the application server, the security evaluation server, the token generation server and the gateway are realized, the security of the application server deployed on the cloud when accessing the intranet data is improved, and the problem of failure of a traditional boundary protection mode caused by network boundary fuzziness in a traditional network is solved; and a stable, safe and reliable network environment is provided for the application server to access the intranet data.
Owner:EASTCOMPEACE TECH

Short-term photovoltaic power generation power prediction method adapting to weather change

The invention discloses a short-term photovoltaic power generation power prediction method adaptive to weather change, which comprises the following steps of: firstly, acquiring meteorological data around a photovoltaic panel and power data of a photovoltaic module, preprocessing the data, and dividing a training set and a test set according to a proportion; according to the method, a Bi LSTM-Attention model based on ISSA optimization is constructed, photovoltaic power generation power prediction is realized by capturing time sequence characteristics and historical information of input data, meanwhile, a mean square error between a predicted value and a true value is calculated to continuously fit the predicted value, prediction model parameters can be updated, model self-learning is realized, and the prediction efficiency is improved. And the accuracy of the short-term photovoltaic power prediction value of the prediction model is further improved. According to the method, the short-term prediction precision of the photovoltaic power generation power under different weather conditions is improved, so that a photovoltaic grid-connected system is helped to respond to the control parameter design of the power grid stability requirement, and the support capability of photovoltaic power generation on the power grid is improved.
Owner:HUANENG JIANGSU COMPREHENSIVE ENERGY SERVICE CO LTD +1

Legal service management system based on block chain

The invention relates to the field of legal service management, and discloses a legal service management system based on a block chain, and the system comprises the following modules: a block chain network, an intelligent contract module, a data storage module, a user interface module, a feedback and monitoring module and a user management module, the non-tampering property and the transparency are ensured; the intelligent contract module automatically executes contract terms and supports intelligent management; the data storage module adopts a hierarchical structure, and on-chain data and off-chain data are stored in a distinguished manner, so that the storage and access efficiency is optimized; and the user interface module provides user-friendly operation experience through a visual tool. By using the block chain technology, all contract execution and compliance audit data are encrypted and stored in a distributed mode, it is ensured that tampering is avoided and whole-course traceability is achieved, and a user and related mechanisms can verify the authenticity and integrity of the contract data at any time.
Owner:BEIJING POWER LAW INTELLIGENT TECH CO LTD

File transmission protection method, system and equipment based on multiple encryption algorithms

The invention discloses a file transmission protection method, system and device based on multiple encryption algorithms, and relates to the technical field of information, and the method comprises the steps: selecting a target file needing to be transmitted, carrying out the preprocessing, and generating file fragments; analyzing the sensitivity of each file fragment, and performing hierarchical encryption processing to obtain an encrypted fragment set; selecting a steganography carrier file, and embedding the encrypted fragments into the carrier file to generate a steganography index table; generating a dynamic session key based on the confusion key pool, encrypting the steganographic file transmission layer and embedding a dynamic key generation parameter; the receiving end generates a session key according to the transmission message header, decrypts the transmission layer data, extracts the steganographic file and decrypts the steganographic file; recombining the decrypted and recovered fragmented data into a complete file according to an identifier sequence; by dynamically matching the steganography carrier file, the efficient embedding of the fragmented data and the generation of the steganography index table are realized, and the concealment and the adaptability in the transmission process are ensured.
Owner:SUZHOU OMEGA NETWORK TECH CO LTD

High-quality metal punch forming forging device and method

The invention relates to the technical field of metal stamping machining, in particular to a high-quality metal stamping forming forging device and method.The high-quality metal stamping forming forging device comprises a base, a support is fixedly installed at the upper end of the base, and a groove plate is fixedly installed in the middle of the upper end of the base. When the punching plate and the groove plate are subjected to die assembly, a shaping plate, a third connecting rod, a fourth spring and an extrusion plate are driven to descend synchronously, the extrusion plate is gradually in contact with an elastic part, and the extrusion plate, the third connecting rod and the shaping plate are driven to suspend, slide on a supporting frame and compress the fourth spring under the resistance of the elastic part; and at the moment, the elastic piece gradually deforms until being separated from the extrusion plate, at the moment, the shaping plate, the third connecting rod and the extrusion plate are pushed to rapidly descend and reset under the action of the fourth spring, the shaping plate is convenient for tamping the stamping plate after die assembly, a good auxiliary effect is achieved on shaping of the metal sheet, and then the stamping quality of the metal sheet is improved again.
Owner:JIANGSU YANGYUAN METAL MFG CO LTD

Deep learning-based cross-dataset magnetic resonance multi-modal super-resolution image synthesis method

The invention discloses a cross-dataset magnetic resonance multi-mode super-resolution image synthesis method based on deep learning, and relates to the field of magnetic resonance imaging. An unsupervised method in deep learning is utilized, and the architecture of a generative adversarial network is adopted, so that the synthesis of a magnetic resonance multi-mode super-resolution image is realized. Carrying out data preprocessing on the image, wherein the data preprocessing comprises registration, slicing and normalization; constructing a high-frequency template, performing FFT (Fast Fourier Transform) on the data to obtain a K space, multiplying a K space image by the high-frequency template to obtain high-frequency information of the K space, and performing IFFT to obtain high-frequency information of an image domain; the prepared image and the high-frequency information thereof are fed into the network as inputs. And through network training, synthesis of multi-modal data is realized. And constructing an image degradation algorithm of the super-resolution reconstruction network. And constructing a network architecture for super-resolution image reconstruction, and inputting the degraded image and the original real image into a network for training to obtain a high-resolution multi-modal magnetic resonance image.
Owner:XIAMEN UNIV

DSL-based intelligent dialogue implementation method, device and equipment for generating SQL (Structured Query Language)

The invention discloses an intelligent dialogue implementation method, device and equipment for generating SQL based on DSL, and the method comprises the steps: responding to an intelligent dialogue instruction of a user terminal, obtaining current user dialogue data corresponding to the intelligent dialogue instruction, and carrying out the intention recognition to obtain a current intention recognition result; correspondingly generating a current DSL script based on the current intention recognition result and a specific domain language script generation strategy; correspondingly generating a current SQL script based on the current DSL script and the script conversion strategy; and obtaining a current query result in a local database based on the current SQL script, generating a current display result corresponding to the current query result, and sending the current display result to the user terminal. According to the embodiment of the invention, the dialogue data of the current user can be firstly subjected to intention recognition and converted into the DSL script and then converted into the SQL script, so that the SQL script obtains the corresponding data from the database, and the support capability of complex query and the accuracy rate of data query are improved.
Owner:BEIJING LINGYI VISION TECH CO LTD

Classroom student attention assessment method and system based on multi-source feature fusion

The invention discloses a classroom student attention assessment method and system based on multi-source feature fusion. According to the invention, face recognition is carried out through the face detection unit of the system, occurrence frequencies of different emotional states of students are obtained through a trained student expression recognition neural network model containing four expression discrimination blocks in the expression recognition unit, and fatigue times of the students are obtained through the fatigue detection unit. The number of times of abnormal head postures of the students is obtained through the head posture estimation unit, finally attention evaluation parameters of the students are obtained through an extreme learning machine model of the attention evaluation unit, and then the attention states of the students in the class are evaluated and displayed. According to the method, a more efficient dynamic student expression recognition method can be provided, real-time and accurate classroom feedback is provided for teachers, optimization and implementation of personalized teaching strategies are supported, longitudinal extension of teaching of the teachers and transverse extension of learning modes of the students are facilitated, and new talents are expanded to cultivate a new normal form.
Owner:ZHEJIANG UNIV

Real-time regulation and control test method and system for power frequency magnetic field of electric energy meter

The invention discloses a real-time regulation and control test method and system for a power frequency magnetic field of an electric energy meter. The method comprises the steps of monitoring power frequency magnetic field intensity and distribution in a laboratory in real time, performing magnetic field data preprocessing, capturing frequency characteristics of magnetic field signals through a frequency domain multi-scale decomposition algorithm, and adjusting output of a magnetic field generator in real time by using a multi-layer nested adaptive feedback control algorithm on the basis of frequency domain analysis. Accurate magnetic field regulation and control are realized; and uploading test data to a cloud platform, dynamically adjusting a test scheme by using a multi-dimensional fuzzy logic algorithm, generating hidden variables through an enhanced time sequence prediction algorithm, performing time sequence prediction, evaluating performance parameters of the electric energy meter in a power frequency magnetic field environment, and providing support for real-time regulation and control test of the electric energy meter. By analyzing the prediction result, the performance parameters of the electric energy meter in the power frequency magnetic field environment are evaluated, support is provided for real-time regulation and control testing of the electric energy meter, and optimal regulation and control of the magnetic field can be achieved.
Owner:STATE GRID ZHEJIANG ELECTRIC POWER CO MARKETING SERVICE CENT +1

Tree painting projection data collection and analysis system and method

The invention relates to a tree painting projection data collection and analysis system and method, and the system comprises a data collection module, a data preprocessing module, a feature extraction module, a quantitative analysis module, a classification and prediction module, and a result evaluation module. The modules cooperate with each other to realize standardized processing, feature extraction, quantitative analysis, intelligent classification and prediction and result evaluation of data. According to the method, the holographic theory and the Ama pothole theory are combined, the drawing features are finely analyzed through the cross-modal comparative learning and graph neural architecture search combined algorithm, a scientific and objective psychological data acquisition and analysis method is provided, the diagnosis sensitivity and specificity are improved, a powerful tool is provided for clinical psychological assessment, and the method is suitable for clinical psychological assessment. The method has important clinical and research values, and has wide application prospects in the fields of psychological problem screening, social psychological services, judicial, public security, marriage matching, talent selection and the like.
Owner:CHONGQING HOLOGRAPHIC PAINTING INTELLIGENT TECHNOLOGY CO LTD

Big data processing method and system for realizing mixed data analysis

The invention provides a big data processing method and system for realizing mixed data analysis, and the method comprises the steps: receiving real-time data streams from different sources, and enabling the real-time data streams to comprise structured data and unstructured data; based on a data fusion logic in a pre-constructed dynamic data fusion framework, the structured data and the unstructured data are fused to obtain fused data, and the data fusion logic comprises a multi-level fusion logic and a dynamic weight adjustment mechanism; carrying out abstraction processing on the fused data to obtain a data view; based on the data view, defining an analysis task, and executing the analysis task to obtain an analysis result; according to the technical scheme provided by the invention, efficient, real-time and flexible mixed data analysis is realized, and the overall performance and support capability of big data processing are improved.
Owner:BEIJING SHUYANG SMART TECH CO LTD

Intelligent neural navigation system for neurosurgery department and use method of intelligent neural navigation system

The invention relates to an intelligent neural navigation system for neurosurgery and a use method thereof.The intelligent neural navigation system comprises an image collecting and processing unit, an intelligent planning unit, a positioning and tracking unit, a visual interaction unit and a data management and updating unit. The optimal operation scheme is selected through operation simulation operation, so that a doctor is helped to master the condition of a patient more clearly, personalized adjustment can be carried out in real time, the operation scheme better fits the actual condition of the patient and the operation habit of the doctor, and the success rate and the quality of an operation are improved. Meanwhile, an optical positioning sensor and an electromagnetic positioning sensor are integrated, accurate position information of the surgical instrument and the area, needing to be treated, of the patient is obtained in real time, operation of the surgical instrument is accurately guided, then it is ensured that the surgical instrument is accurately matched with the preoperative planned path, and mistaken damage to surrounding normal tissue in the surgical process is reduced; and the accuracy and the safety of the operation are improved.
Owner:HUZHOU NO 1 PEOPLES HOSPITAL

Sleep improvement environment sound control auxiliary method and system

The invention relates to the technical field of sleep data processing, in particular to a sleep improvement environment sound control auxiliary method and system. The method comprises the following steps: acquiring sleep state data; performing sleep state feature extraction according to the sleep state data to obtain sleep state feature data; performing environmental sound type selection according to the sleep state feature data to obtain environmental sound type data; according to the environment sound type data and the sleep state feature data, environment audio rate adjustment and environment volume adjustment are carried out, environment audio rate adjustment data and environment volume adjustment data are obtained respectively, and sleep improvement environment sound control auxiliary work is carried out. According to the invention, the system can better adapt to the long-term sleep mode change of the user, and can help the user gradually establish a healthier sleep habit through long-term adjustment and optimization, thereby realizing long-term improvement of the sleep mode.
Owner:THE FIRST AFFILIATED HOSPITAL OF NAVAL MEDICAL UNIVERSITY OF CHINESE PEOPLES LIBERATION ARMY

Data acquisition method and system based on edge calculation

The invention relates to the technical field of data acquisition, and particularly discloses a data acquisition method and system based on edge computing, which are applied to edge computing of the Internet of Things, and comprises the following steps: acquiring multi-source target information according to the Internet of Things, and classifying the multi-source target information to obtain multi-source classification data, the multi-source classification data comprises structured data, unstructured data, time series data and cross-domain data; and establishing a multi-source data index according to the structured data, the unstructured data, the time series data and the cross-domain data, and acquiring a data acquisition frequency set according to the multi-source data index. According to the method, the comprehensiveness and the accuracy of data quality evaluation are ensured by obtaining the first data evaluation value, the second data evaluation value, the third data evaluation value and the fourth data evaluation value of the structured data, the unstructured data, the time series data and the cross-domain data, and the problems that evaluation is not comprehensive and quality changes are not monitored are solved.
Owner:HANGZHOU YUANSHI TECH CO LTD

Resource allocation and task unloading method and system for NOMA-assisted multi-unmanned aerial vehicle edge computing

The invention relates to the technical field of unmanned aerial vehicle edge computing, in particular to a resource allocation and task unloading method and system for NOMA-assisted multi-unmanned aerial vehicle edge computing. The method comprises the following steps: deploying an unloading architecture in a NOMA-assisted multi-unmanned aerial vehicle edge calculation scene, defining related parameters of unmanned aerial vehicles and user equipment, clustering the user equipment, and establishing a network communication model; based on a network communication model, establishing a calculation model, determining the trajectory of the unmanned aerial vehicle, and calculating a joint optimization strategy of resource allocation and task unloading proportion; determining an objective function and a constraint condition of an optimization problem according to the system model; an optimization problem is converted into a Markov decision process, states are normalized, an MSAC algorithm is adopted, multiple unmanned aerial vehicles share a neural network, the Markov decision process is solved, and joint optimization of a task unloading proportion, resource allocation and multiple unmanned aerial vehicle trajectories is realized according to a solving result. According to the method, the minimization of the total maximum time delay of all the user equipment in the NOMA-assisted multi-unmanned aerial vehicle edge computing system is realized.
Owner:SUN YAT SEN UNIV +1

Customer support and feedback analysis processing method based on large language model

The invention discloses a customer support and feedback analysis processing method based on a large language model, and the method comprises the following specific steps: obtaining customer support and feedback data, and judging whether the customer support and feedback data are of a voice type or not; preprocessing the client support and feedback data to obtain input data of a large language model; based on a plurality of independent large language models, performing sentiment analysis, theme recognition and question classification on the input data at the same time to obtain corresponding analysis results; scoring the analysis results and selecting the analysis result with the highest score as an initial optimal solution; circularly feeding back the initial optimal solution to a plurality of independent large language models for further analysis, and obtaining a target optimal solution through convergence evaluation; and matching the target optimal solution with the knowledge base. By combining the large language model and the knowledge base, client support requests and feedback data are processed in real time, the response speed and accuracy are improved, deep feedback analysis is provided, and service decisions are supported.
Owner:IOL WUHAN INFORMATION TECH CO LTD

Three-dimensional diversified notching equipment with adjustable notch

The invention discloses three-dimensional diversified notching equipment with an adjustable notch, and relates to the technical field of notching equipment.The three-dimensional diversified notching equipment comprises a rack and an adjusting mechanism, the adjusting mechanism comprises a supporting plate, an air cylinder is installed in the middle of the outer side of the supporting plate, and a sliding sleeve is fixedly installed at the telescopic end of the air cylinder; a bending guide rod is fixedly installed at the position, close to the sleeve, of the side of the outer side of the sliding sleeve, a cross beam is fixedly installed in the middle of the outer side of the sliding sleeve, a notch assembly is installed at the position, close to the linear driver, of the bottom of the cross beam, and the notch assembly comprises a C-shaped sliding block, and a flat plate is fixedly installed at the bottom of the C-shaped sliding block; and rotating connectors are installed at the corresponding positions of the outer sides of the flat plates, servo motors are installed at the rotating ends of the bottoms of the rotating connectors, and cutting cutterheads are fixedly installed at the output ends of the servo motors. According to the three-dimensional diversified incision equipment with the adjustable incision, the adjustable effect is achieved, the incision can be adjusted, the incision is diversified, and cutting is safe and reliable.
Owner:HEBEI OMLONG MASCH CO LTD

Uncoiling mechanism for pipeline production

The utility model provides an uncoiling mechanism for pipeline production, and belongs to the technical field of pipeline production. The uncoiling mechanism for pipeline production comprises a base, the base comprises a lapping rod seat, a track plate is fixedly installed on one side of the bottom of the lapping rod seat, a trolley is arranged on the top of the track plate, a main shaft is rotationally connected to one side of the lapping rod seat, a plurality of telescopic rod grooves are formed in the surface of the main shaft, and a plurality of expansion and contraction mechanisms are arranged on the outer side of the main shaft. The expansion and contraction mechanism comprises a first telescopic rod and a floating plate, an inserting hole is formed in the top of the output end of the first telescopic rod, a connecting column is fixedly installed at the bottom of the floating plate, the connecting column is inserted into the inserting hole, a fixing hole is formed in one side of the connecting column, and a screw hole is formed in one side of the inserting hole; according to the expansion and contraction mechanism, the floating plate of the expansion and contraction mechanism can be conveniently replaced according to needs, and the expansion and contraction mechanism has high practical value.
Owner:TONG GANG JI TUAN JI LIN SHI HAN GUAN YOU XIAN ZE REN GONG SI

Shale alternating load and multi-field coupling simulation analysis platform and method

The invention provides a shale alternating load and multi-field coupling simulation analysis platform and method, and belongs to the technical field of shale alternating load and multi-field coupling simulation analysis. The shale alternating load and multi-field coupling simulation analysis platform comprises a data acquisition module, a real-time monitoring module, a main control module, an alternating load simulation module, a multi-field coupling simulation module, a data analysis processing module, a cloud storage module and a display module. According to the shale alternating load and multi-field coupling simulation analysis method, a multi-field coupling simulation module, a real-time monitoring module, a data analysis processing module and the like are integrated, and the behavior of shale under the complex geological conditions and the alternating load effect can be more comprehensively analyzed. According to the invention, the maximum stress distribution, strain accumulation and fatigue life of shale under periodic bending alternating load can be accurately predicted through the alternating load simulation module; various shale data analysis methods and algorithms are integrated through the data analysis processing module, and efficient processing of experimental shale data is achieved.
Owner:CNOOC TIANJIN BRANCH

Method and system for evaluating operation risk of unmanned distribution vehicle

The invention discloses a method for evaluating the operation risk of an unmanned distribution vehicle, and the method comprises the following steps: dividing an operation region: dividing the operation region of the unmanned distribution vehicle into a plurality of honeycomb-shaped land parcels, and guaranteeing that the land parcels are not overlapped and completely cover the operation region; key nodes are determined; land block congestion probability calculation: for each honeycomb land block, calculating a truncation mean value of congestion probabilities of all key nodes in the honeycomb land block, and selecting a maximum value from the truncation mean value as an overall congestion probability of the land block; and distribution resource configuration: according to the congestion probability of each cellular land parcel, determining the suitable delivery amount of unmanned distribution vehicles in the land parcel and the number of safety officers responsible for handling potential accidents. According to the method, key nodes of risks in urban traffic operation can be identified, the regional risk assessment method for unmanned distribution vehicle operation is provided from the two dimensions of congestion and accidents, and unmanned distribution vehicle delivery strategy constraints are formed.
Owner:BEIJING SMART CAR MZONE CO LTD

Fire coupling fuse machine for mechanical production

InactiveCN119116380Aavoid affecting lengtheasy to insertTubular articlesCouplingPhysics
The invention discloses a fire coupling fuse machine for mechanical production, and relates to the technical field of fuse machines. The device comprises a heating plate, the heating plate is arranged to be circular and used for melting the ends of different fire couplings, a driving assembly is fixedly connected to the top of a base, the inner side face of the driving assembly is fixedly connected with the outer side face of the heating plate, and the bottom of a splicing assembly is fixedly connected with the side, away from the base, of a sliding table air cylinder. The splicing assembly is fixedly connected with the output end of the sliding table air cylinder, the auxiliary assembly is fixedly connected with the top of the base, the splicing assembly can drive the fire coupling to quickly get close to and get away from the base, the heating plate is taken out, the situation that the melting part of the end of the fire coupling is torn down due to direct taking out of the heating plate is avoided, and the length of the spliced fire coupling is not affected; and the auxiliary assembly can support the fire coupling, so that the fire coupling is conveniently inserted into the splicing assembly, the fire coupling is prevented from tilting when the splicing assembly is inserted, and the influence on fixation of the fire coupling is avoided.
Owner:GUANGDONG DAAN FIRE FIGHTING WATER ELECTRICITY & AIR-CONDITIONING ENG CO LT

A dynamic simulation method of flood inundation in digital twins of small and medium-sized watersheds based on UE5

The present invention discloses a method for dynamic simulation of flood inundation of digital twins of small and medium-sized watersheds based on UE5. It includes the following steps: step one: construct a two-dimensional hydrodynamic numerical model; step two: create a flood inundation simulation UE5 plug-in project; step three: create a flood role class; step four: construct a method for drawing triangular mesh primitives of flood models; step five: construct a method for rendering flood hydrological characteristics and flood flow patterns; step six: realize the dynamic simulation process of digital twin flood inundation. The present invention realizes the dynamic rendering and high-fidelity visualization of large-scale flood models in the three-dimensional scenes of digital twins of small and medium-sized watersheds, expresses the multi-dimensional flood inundation numerical simulation results such as water level, water depth, flow velocity, flow direction, as well as complex flood flow patterns such as backflow, convergent flow, bifurcated flow, floodplain flow, turbulence, etc., improves the authenticity and accuracy of flood inundation simulation, and is conducive to enhancing the decision-making support capabilities of flood risk assessment and flood control plans in small and medium-sized watersheds.
Owner:长江信达软件技术(武汉)有限责任公司

Method and system for quickly acquiring effective data in power-on process, vehicle and medium

The invention relates to a method and a system for quickly acquiring effective data in a power-on process, a vehicle and a medium. The method comprises the following steps of: equally dividing a DFlash space in an embedded chip into two sectors S0 and S1; after power-on, the states of the two sectors are judged firstly, WL traversal is conducted on the two sectors according to the sequence of addresses from back to front, when data are not all zero, a state page is searched and recognized, and the validity of the sectors is determined according to the state page; if all the data are 0, an effective state page is constructed, and the sector state is initialized; if S0 or S1 is valid, traversing sectors from back to front, and detecting and processing valid data; if the sectors S0 and S1 are valid at the same time, judging a new sector and an old sector according to the size of the state page number, and erasing the old sector; in the running process of the system, updating the serial number and the physical address of correctly written data into a cache block variable; and when the system is powered off, updating and writing of the cache block are carried out. According to the invention, effective data can be rapidly obtained in the power-on process.
Owner:辰致汽车科技集团有限公司

Self-adaptive multilingual inter-translation system

The invention discloses a self-adaptive multi-language inter-translation system, and relates to the technical field of multi-language inter-translation, and the self-adaptive multi-language inter-translation system comprises a voice acquisition module, a language analysis module, a semantic recognition module, a bidirectional translation module and a self-adaptive learning module. The translation process is continuously optimized by analyzing the user feedback and the translation result, so that the translation quality can be continuously improved along with time and data accumulation, meanwhile, the forward and reverse translation function provided by the bidirectional translation module ensures that the user can be well supported whether inputting or receiving information, and the user experience is improved. A user can switch languages at any time according to needs, so that communication is smoother, and free flow of information and communication of multi-culture are promoted.
Owner:山东现代学院

Production method of green sand as-cast high-plasticity nodular cast iron QT800-5

The invention relates to the field of metal material casting, and discloses a production method of green sand as-cast high-plasticity nodular cast iron QT800-5, which comprises the following steps: preparing pig iron, waste steel and foundry returns, and using auxiliary materials such as a silicon carbide pretreating agent, a high-temperature graphitization carburant, a rare earth magnesium silicon iron nodulizing agent, a silicon barium nucleating agent and a silicon strontium nucleating agent to prepare the green sand as-cast high-plasticity nodular cast iron QT800-5. The purity and component stability of molten iron are ensured; in the smelting process, purification and adjustment are carried out through temperature control and segmented addition of auxiliary materials, then spheroidizing is carried out through a pouring method, and the microscopic structure of a casting is optimized through ladle-to-ladle inoculation and stream inoculation; the final casting has excellent mechanical properties including the tensile strength larger than or equal to 800 MPa, the yield strength larger than or equal to 480 MPa, the elongation larger than or equal to 5% and the matrix pearlite content larger than or equal to 80%. The production process disclosed by the invention is simplified, is suitable for large-scale industrial production, and has a wide application prospect in lightweight application requiring high-strength and high-plasticity materials.
Owner:SHANDONG HUXIWANG GRP FOUNDRY CO LTD

Clustering-based autism diagnosis method for cross-domain facial expression recognition

The invention discloses an autism diagnosis method for performing cross-domain facial expression recognition based on clustering. The method comprises the following steps: S1 to S4 are source domain model training parts; s1, acquiring a source domain facial expression image; s2, using a large model CLIP to initialize a pre-training model, and preprocessing an input face image; s3, initializing deep learning training conditions, freezing large model parameters, and only training Adapter and a classification module; s4, after the model is trained, facial expression images can be classified, and a trained source domain model weight is also obtained; s5-S10 are target domain model training and autism diagnosis parts. S5, inputting a face video (image sequence) of each child; s6, using the trained source domain model weight to initialize the model, and preprocessing a non-label face image; s7, training a deep learning model, freezing large model parameters, and only training Adapter and a classification module; and S8, according to expressions and facial features classified by the model, domain self-adaption is carried out through a clustering-based dynamic pseudo tag generation module. S9, classifying a facial expression sequence by using the model subjected to domain self-adaption, and performing autism classification by using a long-short-term memory network; and S10, obtaining a diagnosis result.
Owner:TIANJIN UNIVERSITY OF TECHNOLOGY

Three-dimensional digital auxiliary system based on ceramic painting creation

The invention discloses a three-dimensional digital auxiliary system based on ceramic painting creation. The three-dimensional digital auxiliary system comprises a three-dimensional scanning system used for converting a ceramic painting into a three-dimensional digital model; the digital image processing system is used for adjusting digital images of the ceramic painting works and repairing and enhancing the images; the three-dimensional modeling system is used for constructing a three-dimensional model of the ceramic painting works; the virtual reality system is used for displaying the three-dimensional model of the ceramic painting works; the artificial intelligence system is used for carrying out deep learning and analysis on the ceramic painting works and providing various auxiliary functions; according to the invention, a creator can quickly scan, process, model and virtually display the works through a digital technology, so that the creation period is shortened, the creation efficiency is improved, the system can intelligently evaluate and suggest the ceramic painting works, the creator is helped to discover and improve the defects, and the quality of the works is improved.
Owner:JIANGXI VOCATIONAL & TECH COLLEGE OF CERAMIC ARTS & CRAFTS

Construction method and construction device of local knowledge graph

The invention provides a construction method and device for a local knowledge graph, and the construction method comprises the steps: extracting a first concept from the multi-text data of a local database, and carrying out the classification and layering of the first concept; and confirming and supplementing the classified and layered first concepts, and optimizing the first concepts into a plurality of second concepts. And segmenting multi-text data into a plurality of text paragraphs in advance, and matching and associating the text paragraphs with the second concept. And respectively extracting a plurality of local concepts and relationships thereof from the associated text paragraphs, and constructing an entity relationship multi-tuple. And integrating similar local concepts in the entity relationship multi-tuple into the same local concept. And analyzing the similarity of all the relationships in the plurality of entity relationship multi-tuples, and evaluating the relevance among all the entity relationship multi-tuples. And based on this, obtaining the constructed knowledge graph. According to the semi-automatic construction method and device, on the basis that expert knowledge is well utilized, the method does not excessively depend on manual construction rules, and the reasoning and understanding ability of a large model is utilized to the maximum extent.
Owner:SAIC VOLKSWAGEN AUTOMOTIVE CO LTD

Prestressed concrete pipe pile connecting device

The invention discloses a prestressed concrete pipe pile connecting device, and relates to the technical field of pipe pile connecting structures, the prestressed concrete pipe pile connecting device comprises a lower pipe connecting pile, a sealing structure is arranged above the lower pipe connecting pile, an upper pipe connecting pile is arranged above the sealing structure, and mounting screws are arranged on the outer side of the sealing structure; a splicing base structure and a connecting base structure are arranged in the sealing structure, assembling structures are arranged on the sides, away from each other, of the splicing base structure and the connecting base structure, and a pressure applying connecting rod structure is arranged in the splicing base structure and the connecting base structure in a penetrating mode. The splicing base structure comprises a connecting inner barrel, a prismatic disc is fixedly connected to the outer surface of the connecting inner barrel, and an elastic rod fixing base is fixedly connected to the interior of the prismatic disc. Fixing and connection are achieved by means of deformation of an expansion strip of an expansion barrel extruded by a compression rod under the gravity of the upper pipe connecting pile, so that rapid positioning is achieved when the lower pipe connecting pile and the upper pipe connecting pile are connected; and butt joint installation is facilitated.
Owner:JILIN WEIHENG CEMENT PRODUCTS CO LTD

Keyboard key pressure identification method and device based on deep learning

The invention relates to the technical field of machine learning, in particular to a keyboard key pressure identification method and device based on deep learning. The method comprises the following steps: acquiring initial pressing stroke data of a single key of a keyboard; performing pressure measurement on a single key corresponding to the initial pressing stroke data by using a pressure sensor to obtain keyboard key pressure measurement data; keyboard pressing effective stroke screening is carried out on the initial pressing stroke data of the single key of the keyboard through the keyboard key pressure measurement data, and keyboard pressing effective stroke data are obtained; obtaining keyboard key structure data; and performing three-dimensional pressing depth identification on the keyboard key pressure measurement data according to the keyboard pressing effective stroke data to generate keyboard three-dimensional pressing pressure identification data. According to the method, through a multi-step technology of accurate pressing stroke screening, three-dimensional pressure distribution identification, mistaken touch correction, contact optimization and the like, the accuracy and error interference of keyboard key pressure identification are improved.
Owner:渴创技术(深圳)有限公司