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

109results about How to "Reduce time delay" patented technology

Intelligent regulation and control method for coal mine ventilation system based on environmental perception

The invention discloses a coal mine ventilation system intelligent regulation and control method based on environmental perception, and relates to the technical field of coal mine ventilation system intelligent regulation and control, and the method comprises the following steps: collecting environmental data of different areas of a mine, including gas concentration, temperature and humidity, air velocity and oxygen content, and monitoring the operation state of ventilation equipment in real time; data of all the sensors are synchronously processed through the data fusion technology, and a unified environment sensing model is generated. According to the invention, through cooperative work of the expert system and deep learning, real-time monitoring and emergency plan execution under extreme working conditions are realized, and the response speed and decision accuracy are improved. A reinforcement learning algorithm is adopted to optimize ventilation line switching, the adaptive capacity and redundancy guarantee of the system are enhanced, and it is ensured that airflow is not interrupted at the critical moment. Through abnormality comparison of the knowledge base and the rule base, false alarm and misjudgment are reduced, system efficiency is improved, operation burden is relieved, and safety and stable operation of mine personnel are guaranteed to the maximum extent.
Owner:HUATING COAL GRP CO LTD +1

Landslide geological disaster monitoring and early warning system based on multi-means fusion

The invention relates to the technical field of geological disaster monitoring, in particular to a landslide geological disaster monitoring and early warning system based on multi-means fusion, which comprises a data acquisition module, a data fusion module, a landslide prediction module, a landslide disaster intelligent partition and response module and an early warning transmitting module, the data acquisition module acquires landslide related data in real time; the data fusion module is used for fusing landslide related data from different sources; the landslide prediction module is used for predicting the occurrence probability of the landslide; the landslide disaster intelligent partition and response module combines landslide related data and geologic structures monitored in real time, dynamically adjusts post-disaster response measures, and generates early warning information; and the early warning signal sending module automatically sends an early warning signal based on the generated early warning information. According to the invention, potential risks can be found in time in the early stage of landslide occurrence, and the accuracy and timeliness of disaster early warning are greatly improved.
Owner:LIAONING TENTH GEOLOGICAL BRIGADE CO LTD

Intelligent bridge reinforcement decision generation method, device and equipment based on damage identification

The invention relates to the technical field of data processing, and discloses an intelligent bridge reinforcement decision generation method, device and equipment based on damage identification. The method comprises the following steps: carrying out bridge damage identification and evaluation on a bridge state data set to obtain a bridge damage characteristic spectrum; performing intelligent decision analysis on the bridge damage characteristic spectrum, generating a preliminary reinforcement scheme, and obtaining a candidate reinforcement strategy set; performing parametric modeling and multi-scale simulation on the candidate reinforcement strategy set, and performing coupling calculation evaluation on a reinforcement effect to obtain an optimized reinforcement scheme; virtual construction planning is conducted on the optimized reinforcement scheme, a construction process model is generated through an intelligent scheduling algorithm, and a target construction scheme is obtained; and monitoring and feeding back the target construction scheme in real time, and dynamically optimizing the construction process through an adaptive control algorithm to obtain a target intelligent reinforcement implementation scheme. The intelligent bridge reinforcement decision generation efficiency and accuracy based on damage identification are improved.
Owner:ZHENGZHOU COMM PLANNING SURVEY & DESIGN INST

Method and device for improving data through efficiency based on large model and medium

The invention discloses a method and equipment for improving data nonstop efficiency based on a large model, and a medium, belongs to the technical field of large models and data processing, and aims to solve the technical problem of how to reduce time delay of data transmission and processing in a large data processing process, ensure integrity and consistency of data, and improve data nonstop efficiency. According to the technical scheme, the method comprises the steps that multi-source data collection and processing are conducted, specifically, real-time data streams are integrated and synchronized in batches, data are efficiently collected from a database, an API, a file and Internet of Things equipment through a data source adapter, then preprocessing and optimization preprocessing are conducted on the data, and an original data set is obtained; feature engineering: performing feature extraction and feature conversion on the original data set to obtain a pre-training data set; training and optimizing a large model; model deployment and integration: the trained model is exported as a SavedModel format of deployable TensorFlow or a TorchScript format of PyTorch, and real-time data pushing is realized through an API (Application Program Interface) according to a data direct requirement; and a real-time analysis engine.
Owner:SHANDONG LANGCHAO YUNTOU INFORMATION TECH CO LTD

NOMA-assisted cloud side-end communication calculation method based on digital twinning

The invention belongs to the technical field of information, and discloses a digital twinning-based NOMA-assisted cloud side end communication computing method, which comprises the following steps of: constructing a cloud side end cooperative communication computing architecture, considering the problems of terminal isomerism and edge server load balance, partially unloading a computing task, and selectively transmitting the unloaded part to a local edge server for computing. Or selecting a local edge server as a relay node, further transmitting to a third-party edge server or a cloud server for cooperative computing, considering the security problem of edge computing, formulating the problem, constructing an optimization target of resource allocation and task unloading decision and a corresponding constraint condition, and converting into a multi-agent MDP; and the MADDPG algorithm is used for solving in the digital layer, real-time interaction with the physical layer is realized to complete strategy issuing, cloud side-end collaborative communication calculation is realized, the security and accuracy of the problem model are improved, and the Qos demand of the terminal is met.
Owner:NANJING UNIV OF POSTS & TELECOMM

Big data network signal safety early warning system

The invention relates to the technical field of network security analysis, in particular to a big data network signal security early warning system. The system comprises a network signal big data stream transmission module, a network signal ratio difference detection module, a network signal division result safety early warning module and a network signal abnormity safety response module. Data acquisition equipment can be deployed at an entrance and an exit of each network equipment, and network signal data real-time acquisition and big data stream type transmission conversion can be carried out, so that a network signal big data stream can be obtained; carrying out time sequence flow size and access frequency statistical analysis on the network signal big data flow, and carrying out network signal ratio difference detection division and abnormal safety early warning processing at the same time to generate a network signal abnormal safety early warning signal; and uploading the network signal abnormity safety early warning signal to a cloud platform to carry out abnormity safety response processing so as to generate a network signal abnormity safety response protection strategy. According to the invention, network signal abnormity can be efficiently monitored in real time and early warning can be provided.
Owner:SHANDONG YOUTH UNIV OF POLITICAL SCI

Optimization method formed through secondary feedback of rider

The invention relates to the technical field of distribution management, in particular to an optimization method formed through secondary feedback of a rider, and the method comprises the steps: S1, building a networking platform, and collecting various information of the rider in real time; s2, a feedback mechanism is established, and a rider feeds back important information encountered in the distribution process in real time; s3, collecting the work data of the rider, and generating a personalized work capability evaluation model; s4, the networked map software collects road information, and establishes a route prediction mechanism in combination with feedback data and historical data; s5, monitoring distribution information of the rider in real time, and providing a processing scheme in case of an emergency; and S6, obtaining distribution information, and learning and optimizing an evaluation model and route planning of the rider. The method is beneficial for greatly improving the flexibility and response speed of the platform to cope with emergencies, ensuring dynamic optimization of the distribution plan of the rider, improving the consumer experience, enhancing the participation sense of the rider, and improving the working enthusiasm and initiative of the rider.
Owner:GUIZHOU SUNSHINE HAINA ECOLOGICAL AGRI CO LTD

Speech recognition method and device, storage medium and electronic equipment

PendingCN119600994AImprove experienceImprove Speech Recognition EfficiencySpeech recognitionText recognitionFeature extraction
The invention provides a voice recognition method and device, a storage medium and electronic equipment, and the method comprises the steps: calling a target pre-training model, carrying out the feature extraction of target voice data, and obtaining the voice feature of each target voice frame in the target voice data; based on the voice feature of each target voice frame, performing clustering processing on the target voice data to obtain a plurality of clustered voice features so as to determine at least one text recognition result; when the target voice data meets the streaming audio data recognition condition, determining audio data representation features under the target voice data based on the plurality of clustering voice features and the at least one text recognition result; and calling a target attention model, and determining a decoding feature of each text recognition result in the at least one text recognition result based on the audio data representation features under the target voice data, thereby determining a target voice recognition result of the target voice data. According to the embodiment of the invention, voice recognition can be quickly carried out on the target voice data.
Owner:DUXIAOMAN TECH (BEIJING) CO LTD

Information retrieval method and device, electronic equipment, storage medium and computer program product

The invention discloses an information retrieval method and device, electronic equipment, a storage medium and a computer program product, and the method comprises the steps: receiving a first query statement input by a user; judging whether a first list contains the first query statement or not to obtain a judgment result; the first list comprises one or more query statements, and each query statement in the first list is associated with zero or one or more answers in a set database; when the judgment result represents that the first list contains the first query statement and the first query statement is associated with one or more answers in the set database, randomly selecting a first answer from the one or more answers, and calculating a first score based on user interaction information of the first answer; and when the first score is greater than a first score threshold value, outputting the first answer as a retrieval result of the first query statement.
Owner:CHINA MOBILE CHENGDU INFORMATION & TELECOMM TECH CO LTD +1

Hydrodynamic three-dimensional model construction method and system based on digital twin rendering

The invention discloses a hydrodynamic three-dimensional model construction method and system based on digital twin rendering, and relates to the technical field of hydrodynamic model construction. According to the digital twin rendering-based hydrodynamic three-dimensional model construction method, historical water flow data and river geographic information of a river are acquired and analyzed, a river three-dimensional model is established based on an analysis result, hydrodynamic simulation is performed, and a hydrodynamic simulation result is evaluated and adjusted, so that the dynamic three-dimensional model is constructed. According to the method, the historical water flow data and the detailed geographic information are integrated to construct the three-dimensional model, and iterative optimization is performed on the three-dimensional model, so that the prediction accuracy of the model can be improved, and the iterative optimization process allows the model to adapt to environmental changes and unforeseen hydrological events, so that the prediction accuracy of the model is improved. Therefore, the applicability and flexibility of the model in practical application are enhanced, the model is further suitable for a dynamic and complex water body environment, and a decision maker can formulate a water resource management strategy based on the most accurate simulation result.
Owner:HARBIN HONGDE YITAI DIGITAL TECH CO LTD

Gas pipe network leakage early warning method and system based on edge calculation

The invention relates to the field of gas pipe network leakage early warning, in particular to a gas pipe network leakage early warning method based on edge calculation, which is applied to an equipment terminal, and comprises the following steps: responding to a leakage monitoring request, and receiving pipe network current data acquired by an acquisition end, the pipe network current data comprising pressure current data and leakage current data; calling a preset screening model to process the pipe network current data to obtain abnormal deviation values, and obtaining effective pipe network data based on the abnormal deviation values and the corresponding data fluctuation thresholds; receiving pipe network annotation data, obtaining hidden layer output values of the pipe network annotation data according to the initial evaluation model, and determining a state output weight based on each hidden layer output value to obtain a pipe network state evaluation model; and inputting the effective pipe network data into the pipe network state evaluation model for evaluation, generating a state evaluation result, processing an abnormal state evaluation result based on a preset early warning strategy, generating leakage evaluation data, and sending the leakage evaluation data to a data center.
Owner:NANJING YIMEIWO ELECTRONICS TECH

Textile traceability method and system based on block chain

The invention belongs to the technical field of textile traceability, and particularly relates to a textile traceability method and system based on a block chain, and the method comprises the steps: analyzing the textile data integrity based on a block chain network, judging whether the textile data is complete or not, analyzing the textile traceability access confidence, and judging whether the textile traceability access behavior is credible or not. And analyzing the textile traceability query result, comparing to obtain textile traceability data, analyzing the textile traceability data state, and comparing to obtain a textile traceability data risk point. According to the method, the problems of inaccurate and missing data possibly existing in traditional textile data traceability related information and incomplete judgment of the textile data traceability access verification state are solved, the whole production resume of a product can be restored more accurately, risk points in a supply chain can be found and positioned favorably, and the quality of the product is improved. And a basis is provided for improvement.
Owner:滨州市检验检测中心(滨州市纺织纤维检验所)

Lightweight remote sensing image small target detection method

The invention discloses a lightweight remote sensing image small target detection method. Through a lightweight convolution module LFC, parameter quantity and calculation quantity required by convolution operation are reduced, and feature extraction and down-sampling are completed on the premise of limited calculation resources and storage space; a receptive field expansion module RFEB is adopted, a receptive field of a backbone network is expanded through multi-branch expansion convolution, local and global context information is fully utilized, and the problem of insufficient feature representation of small targets in a remote sensing image is solved; a hierarchical fusion attention module HFAB is utilized, and spatial attention and self-attention are gradually stacked, so that feature fusion from coarse granularity to fine granularity is realized, and feature representation of a small target is richer; according to the method provided by the invention, on the premise of keeping the target detection precision, the model parameter quantity and the calculation overhead are reduced, the calculation complexity is effectively reduced, and the feasibility of application of a target detection algorithm in edge calculation and real-time monitoring scenes is improved.
Owner:HUNAN UNIV OF SCI & TECH

Branch marketing method based on intelligent matching geographic data and new enterprise information

The invention relates to a website marketing method based on intelligent matching geographic data and newly-opened enterprise information, which comprises the following steps: acquiring detailed information of a business website, creating a basic snapshot information base, and acquiring and preprocessing the newly-opened enterprise information at regular time; converting the website position and the enterprise registration address into latitude and longitude coordinates, and based on a preset matching distance range, screening out a matching website set meeting conditions by using a Haversine formula; performing clustering on stock enterprises corresponding to the matching network point set through a K-Means clustering algorithm, and matching a clustering center in combination with the characteristics of a new enterprise to obtain an optimal network point list; presetting website scoring indexes, calculating website comprehensive scores according to the website scoring indexes, and selecting the website with the highest score as an optimal matching website; and pushing the information of the new enterprise to a customer manager corresponding to the optimal matching network to carry out marketing activities, and if the information is returned, carrying out matching again. According to the invention, the accuracy and efficiency of website marketing are improved, and the service experience of newly opened enterprises is optimized.
Owner:CHINA CONSTR BANK CORP (FUJIAN BRANCH)

Model reasoning method and device, storage medium and computer equipment

The invention provides a model reasoning method and device, a storage medium and computer equipment. The method comprises the following steps: acquiring a pre-stored allocation table and an address recovery table of a target model; wherein the allocation table is a target model used for recording an execution sequence corresponding to nodes in a computational graph captured by the target model in a preprocessing process, and the address recovery table is a mapping relation table of a kernel and parameters constructed according to the computational graph; according to the execution sequence in the allocation table, an address recovery table is inquired, address information of nodes in the computational graph is obtained, and the address information comprises a kernel address and a parameter address of each node; according to the address information of each node, recovering a computational graph of the target model in the reasoning process; and based on the calculation graph, executing reasoning calculation of the target model. Therefore, the model can be inferred according to the computational graph, the operator graph is prevented from being recaptured when the model is inferred, the time delay of cold start of the model is reduced, and the cold start efficiency of the model is improved.
Owner:TSINGHUA UNIVERSITY

Response method and device for interrupt signal of virtual machine, terminal and storage medium

The embodiment of the invention discloses a response method and device for an interrupt signal of a virtual machine, a terminal and a storage medium. The method comprises the following steps: in response to a target trigger operation of external equipment of a virtual machine, obtaining target interrupt information matched with the target trigger operation from a pre-configured interrupt information set, and determining a target virtual processor for processing the target trigger operation; sending a target interrupt signal to the target virtual processor according to the target interrupt information through a target message interrupt controller matched with the target virtual processor; the target interrupt signal has a corresponding first physical address. And determining a second physical address matched with the first physical address according to pre-configured address mapping, and executing the target interrupt signal based on the second physical address through the physical processor to complete interrupt response of the target trigger operation. Through the embodiment of the invention, frequent operation of the virtual machine monitor is avoided, the system overhead is reduced, and the operation efficiency of the virtual machine is improved.
Owner:BEIJING INSTITUTE OF OPEN SOURCE CHIP

A rapid stroke identification method combining TOPSIS and artificial intelligence

The present invention relates to a method for rapid stroke identification combining TOPSIS and artificial intelligence. First, the existence of unilateral muscle strength decline is judged by the degree of horizontal raising of the user's arms, and the muscle strength difference is graded by the angle between the arms; then the degree of slurred speech of the user is analyzed by artificial intelligence speech recognition and combined with the error word rate calculation method; then the position coordinates of the facial feature points are detected by the artificial intelligence facial feature point recognition model, the degree of facial droop is calculated by the TOPSIS method, and finally the risk degree of stroke is rapidly identified by the TOPSIS method by comprehensively grading the muscle strength difference, the degree of slurred speech and the degree of facial droop. The present invention can enable patients and their families to effectively and quickly identify stroke symptoms at home, and automatically shunt stroke patients to corresponding stroke centers for treatment according to different severity of stroke, thereby improving the emergency rescue efficiency and quality of emergency medical rescue services.
Owner:DONGHE SOFTWARE (JIANGSU) CO LTD +2

Emergency notification system and method based on urban emergencies

The invention discloses an emergency notification system and method based on urban emergencies, and the system comprises an information encryption and authentication module which is used for guaranteeing the authenticity and integrity of information and preventing the information from being tampered; the multi-mode transmission module is used for supporting information transmission in text, voice and image forms; the geographic positioning service module is used for sending an alarm according to the position information of the user; the redundant backup mechanism module is used for ensuring stable operation of the emergency notification system; the emergency broadcast module is used for receiving emergency information of the current-level emergency information source and emergency broadcast messages of upper and lower-level emergency broadcast platforms; and the user feedback module is used for collecting the information receiving condition of the user, evaluating the effect and improving the effect. The emergency notification system which is vertically through, comprehensively covered, safe, reliable, accurate and efficient is established, loss caused by disasters and accidents is reduced to the maximum extent, and support is provided for promoting improvement of an emergency management system.
Owner:ZHONGHONG ZHIYUN (BEIJING) TECH CO LTD

Anti-disturbance self-calibration method of inertial navigation equipment for navigation

The invention relates to the technical field of ship navigation, in particular to an anti-disturbance self-calibration method of inertial navigation equipment for navigation, which comprises the following steps: carrying out inertial solution on inertial navigation original data to obtain a solution speed, and subtracting a reference speed from the solution speed to obtain a speed error; performing real-time wavelet transform on the speed error containing the disturbance speed to remove the disturbance speed; taking the speed error subjected to the wavelet transform processing as the observed quantity of a Kalman filter, and obtaining an inertial navigation error parameter by using Kalman filtering; the inertial navigation error parameters are fed back to the inertial calculation process; and repeating the steps until the inertial navigation error parameter estimated by the Kalman filter is converged, and completing calibration. According to the invention, the technical problem that the calibration method in the prior art is difficult to meet the requirements of long endurance and high-precision calibration under the conditions of mooring, anchoring and course change is solved.
Owner:CENT SOUTH UNIV +1

Wireless multi-source data fusion method for multi-component mixing spray gun control

The invention provides a wireless multi-source data fusion method for multi-component mixing spray gun control, which comprises the following steps of: constructing a time sequence vector V, carrying out dimension raising processing and preprocessing on the time sequence vector, sending a signal to a wireless channel, superposing modulation signals of different sensor nodes to obtain a superposed signal, and fusing the superposed signal into a multi-component mixing spray gun; the method comprises the following steps of: acquiring a superposed signal, constructing a mean square error according to the superposed signal and a preset spraying decision function, constructing and solving an optimization problem to obtain an optimal sensor emission signal, sending the optimal sensor emission signal to a decision controller, and directly performing a spraying control decision according to the received signal by the decision controller to control spraying parameters of a multi-component mixing spray gun; according to the spray gun control system, dimension raising processing and preprocessing are conducted on the signals collected by the sensors, the preprocessed signals are directly transmitted to the decision controller, the decision controller directly receives the decision result, the spray gun is controlled more rapidly, and the control precision and effect of the spray gun are improved.
Owner:ZHENGZHOU UNIV +1

Vehicle-end data processing method, vehicle-end device and vehicle-end data processing system

The application relates to a vehicle-end data processing method, a vehicle-end device and a vehicle-end data processing system. The method comprises the following steps: obtaining a target communication message in a communication line during vehicle operation; in the case that a current computing task is received from a cloud server, converting the current computing task into a current processing instruction; processing the target communication message according to the current processing instruction to obtain a current computing result, and uploading the current computing result to the cloud server. The method can realize real-time processing of the target communication message, reduce the time delay of data transmission to the cloud for processing, timely monitor abnormal conditions of the vehicle state, avoid leakage of vehicle-end privacy information, and ensure data security.
Owner:WUHAN LOTUS CARS CO LTD

Resource determination method and apparatus

Disclosed in the present application are a resource determination method and apparatus, which are used, when transmission failure recovery (BFR) occurs, for selecting a more appropriate scheduling request (SR) resource for a physical resource in which transmission failure occurs, thereby improving the transmission reliability of an LRR, and shortening a time delay of the BFR. Provided in the present application is a resource determination method, comprising: determining a physical resource in which transmission failure occurs; and according to an association relationship between a relevant parameter of a scheduling request (SR) resource that is configured or predefined by a network side and a relevant parameter of the physical resource, determining an SR resource for the physical resource in which transmission failure occurs.
Owner:DATANG MOBILE COMM EQUIP CO LTD

Method and device for berthing and unberthing of ship at wharf

The invention provides a ship berthing and unberthing method and device for a wharf and relates to the technical field of wharfs, and the ship berthing and unberthing method for the wharf comprises the steps that when a ship berths in the first direction, whether the first distance between the bow of the ship and a second trestle meets the preset safety distance or not is judged, and if yes, the first trestle is stopped; controlling the ship to enter a berth water area between the first trestle and the second trestle through a reverse cable for connecting the ship with the first abutment and a ship adjusting device; when the ship leaves the berth, the bow is connected with the second abutment through a reverse cable, and the ship is controlled to retreat; and when the ship is driven out of the berth water area by a preset second distance, the stern of the ship is connected with the first abutment through an inverted cable, and the ship is controlled to rotate out of the berth water area through a ship adjusting device. The ship berthing and unberthing efficiency of a wharf can be effectively improved, and the safety risk of berthing and unberthing of a large ship in a harbor basin with a narrow space is reduced.
Owner:CHINA RAILWAY JIUJIANG BRIDGE ENG +1

A supersonic isolated section flow field reconstruction method integrating CNN and FCNN

This invention relates to the field of high-altitude work equipment technology and discloses a method for reconstructing the flow field in a supersonic isolation section by integrating CNN and FCNN. The method includes the following steps: acquiring wall pressure data and schlieren image sequences in a wind tunnel test system; using synchronous light signals for time alignment and preprocessing; constructing a training dataset containing normalized pressure feature vectors and a matrix of real flow field schlieren images; constructing a parallel dual-branch deep learning model; using a convolutional neural network branch to reshape the pressure data into a matrix to extract spatial structure features; and using a fully connected neural network branch to directly extract numerical correlation features. The outputs of both are merged in a feature fusion layer. After optimizing the model parameters using the training dataset, the real-time acquired wall pressure is input into the trained model, and the reconstructed flow field grayscale image is output. This invention solves the problem of difficulty in reconstructing complex flow fields from sparse pressure data and achieves high-precision real-time monitoring of the flow field in a supersonic isolation section.
Owner:HARBIN INST OF TECH

A lightweight method for small target detection in remote sensing images

The present invention discloses a lightweight remote sensing image small target detection method; through a lightweight convolution module LFC, the amount of parameters and the amount of calculation required for the convolution operation are reduced to complete feature extraction and downsampling under the premise of limited computing resources and storage space; a receptive field expansion module RFEB is adopted to expand the receptive field of the backbone network through multi-branch dilated convolution, and make full use of local and global context information to solve the problem of insufficient feature representation of small targets in remote sensing images; a hierarchical fusion attention module HFAB is used to achieve feature fusion from coarse-grained to fine-grained by progressively stacking spatial attention and self-attention, so that the feature representation of small targets is richer; the method provided by the present invention reduces the amount of model parameters and calculation overhead while maintaining the target detection accuracy, effectively reduces the calculation complexity, and improves the feasibility of the target detection algorithm in edge computing and real-time monitoring scenarios.
Owner:HUNAN UNIV OF SCI & TECH

Report generation method and system for multi-source data fusion

The invention provides a multi-source data fusion report generation method and system, and relates to the technical field of data processing, and the method comprises the steps: extracting a first filling lattice in a first report demand, the first filling lattice having a first filling logic; obtaining a first filling parameter of the first filling lattice after the expiration date, and introducing a multi-layer verification mechanism for verification in combination with the first filling logic to obtain a first verification result; when the first verification result reaches a first predetermined constraint, generating a first sequence based on a first filling parameter, the first sequence including a first transverse sequence and a first longitudinal sequence; a multi-parallel verification mechanism is introduced to verify the first transverse sequence or the first longitudinal sequence, and a second verification result is obtained; and when the second verification result reaches a second predetermined constraint, generating a target report. The technical problems that in the prior art, the data quality and accuracy of different data sources are difficult to unify, data verification is insufficient, and then the accuracy and effectiveness of generated reports are poor are solved.
Owner:CHENGDU CHENGTOU YOULIAN TECH CO LTD

Financial regulatory rule dynamic distillation method, apparatus, medium, and device

PendingCN122865709ARealize instant analysisreduce time delay
The application relates to the technical field of financial informatization, and discloses a financial supervision rule dynamic distillation method, device, medium and equipment, which comprises the following steps: preprocessing unstructured rule text, and converting the unstructured rule text into structured training samples based on a logic tree annotation system; generating teacher output results based on the structured training samples, and performing distillation training on a student model by using the structured training samples and the teacher output results to obtain a distillation model; performing constraint decoding on the output process of the distillation model to generate candidate structured executable rules, and performing multidimensional effectiveness verification to determine target structured executable rules, which are deployed into a rule engine of a target business system. The above method forms a complete automatic closed loop from rule text acquisition, structured conversion, model distillation to rule generation and deployment, realizes instant analysis of unstructured rule text, structured extraction and automatic deployment, shortens a rule updating cycle, and reduces maintenance cost.
Owner:ZHONGJINKE INFORMATION TECH CO LTD +1

Gastrointestinal nursing medicine formula optimization system based on data fusion

The invention discloses a parenteral nursing medicine formula optimization system based on data fusion, and relates to the technical field of parenteral nursing. Constructing an infusion amount change curve of different preparation components, performing time sequence alignment on the target physiological parameters and the infusion amount change curve, extracting a fusion feature vector, and inputting the fusion feature vector into a patient metabolism model to output a deviation index, extracting local fusion feature vectors of different preparation components, combining the local fusion feature vectors with the patient metabolism model to output a contribution index, generating an evaluation result according to the deviation index and the contribution index, updating model parameters in the patient metabolism model, and generating formula optimization suggestions; multi-source data can be integrated, the metabolic state of a patient can be monitored in real time, a medication formula is dynamically optimized, and the safety and effectiveness of parenteral nursing are improved.
Owner:AFFILIATED HOSPITAL OF WEIFANG MEDICAL UNIV

Continuous casting submersed nozzle centering detection device

The utility model discloses a continuous casting submersed nozzle centering detection device, which comprises two main bodies which have the same structure and are symmetrically distributed, each main body comprises two cover plates, and the same side edges of the two cover plates are connected through a connecting plate; a handle is arranged at the bottom of the bottom cover plate; a sliding rod is installed between the two cover plates in a sliding mode, a spring is installed in parallel with the sliding rod, and the spring is located between the edges, opposite to the connecting plates, of the cover plates. A scale groove is formed in the cover plate and is parallel to the motion trail of the sliding rod. During detection, the two main bodies clamp the submersed nozzle from the two sides, the sliding rod tightly attached to the spring slides along the sliding rail along with deformation of the spring, the sliding rod points to the scales of the scale grooves in the corresponding positions, and whether the water outlet is centered or not can be rapidly and visually judged by comparing the scale values on the two main bodies.
Owner:JIANGSU LIANFENG ENERGY EQUIP

Information security interconnection method of hybrid space network

The invention provides an information security interconnection method of a hybrid space network. The method comprises the steps of obtaining a communication connection demand requested by a user; based on the communication connection demand, querying a plurality of space network nodes matched with the communication connection demand in a pre-established space network node set, and generating initial routing paths corresponding to the plurality of space network nodes; performing optimization processing on the initial routing paths corresponding to the plurality of space network nodes to generate target routing paths of the plurality of space network nodes; and performing encryption operation on the target routing path of the selected space network node by using a pre-created security policy, and applying the encryption operation to the target routing paths of the remaining plurality of space network nodes in batches. According to the technical scheme provided by the invention, the time delay of data transmission can be remarkably reduced, and the overall efficiency of space network communication is improved.
Owner:CHINA ELECTRONICS CORP 6TH RES INST +1