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

23results about How to "Resolve differences" patented technology

Event extraction method, system and device based on multi-agent collaboration

The invention discloses an event extraction method, system and device based on multi-agent cooperation. The method comprises the following steps: receiving unstructured data, calling at least one second agent by a first agent to identify an entity and a type thereof, and storing a result into an information pool; calling at least one third agent to identify a trigger word and a corresponding event type, and storing the trigger word and the corresponding event type in an information pool; analyzing the trigger word and the event type, and generating an element role set; the fourth agent identifies the unity element role and stores a result in an information pool; segmenting the unstructured data into text units with different granularities, such as sentences, paragraphs and chapters, and generating corresponding context prompt information Prompt; and calling an intelligent agent to perform event identification on each granularity text, fusing event information of different granularities, and generating a final event extraction result. Through cooperative work of multiple agents, more accurate event identification and information integration are realized, and the accuracy and efficiency of event extraction are improved.
Owner:CETC BIGDATA RES INST CO LTD

Protein interaction prediction method based on cross-modal enhanced representation learning

ActiveCN119626312Arich expressionresolve differencesBiostatisticsBiological modelsData miningTRADD Protein
The invention relates to the technical field of protein prediction, and discloses a protein interaction prediction method based on cross-modal enhanced representation learning. According to the method, a Convform module and a Graphform module are designed, and a global attention mechanism is introduced into each module, so that the limitation that only local features or global features are concerned in an existing method is broken through. According to the design, the model can capture the local mode and the global dependency relationship of the protein at the same time, and more comprehensive protein representation is provided. The invention provides a cross-modal enhancement method based on comparative learning. The problem of difference between a sequence mode and a structural mode is solved through an explicit mode alignment process. The method not only can maintain unique information of each mode, but also can give full play to complementarity among the modes, so that richer protein expression is obtained. The cross-protein fusion module provided by the invention can more accurately capture essential characteristics of protein interaction, and the accuracy of PPI prediction is remarkably improved.
Owner:OCEAN UNIV OF CHINA

Auxiliary pathological analysis method of microscope system

The invention provides an auxiliary pathological analysis method for a microscope system, and belongs to the technical field of pathological analysis, and the method comprises the steps: firstly carrying out the gray normalization, denoising and other preprocessing of an obtained pathological section image, and carrying out the illumination equalization processing through a region adaptive histogram equalization algorithm; then, color features of the image are extracted in an LAB color space, a color representation center is calculated, a feature mapping matrix is established, and meanwhile texture features are extracted and fused with the color features; and carrying out dimension reduction on the fused feature vector by using a principal component analysis algorithm, and reserving important feature information. And then, establishing a convolutional neural network model, inputting the feature vectors after dimension reduction, performing training and cross validation by using a labeling data set, and improving the model performance through iterative optimization. According to the invention, the technical problem that the diagnosis and judgment of a doctor are seriously influenced due to inconsistent color expression caused by the difference of shooting conditions of pathological section images observed by a microscope is solved.
Owner:QINGDAO MUNICIPAL HOSPITAL

FPGA-based system for replacing OLED with LCD screen

The invention is applied to the technical field of product communication, and discloses an FPGA (Field Programmable Gate Array)-based LCD (Liquid Crystal Display) screen replacement OLED (Organic Light Emitting Diode) system, which comprises an MIPI (Mobile Industry Processor Interface) decoding unit, an RAM (Random Access Memory) image cache unit, a clock recovery unit, a scaling interpolation unit, an output time sequence unit, an MIPI coding unit, a screen command unit and an ADC (Analog to Digital Converter) sampling unit, and the FPGA selected by the system is only Lattice-XO3. According to the FPGA-based system for replacing the OLED with the LCD screen, the problem that the resolution ratios of the LCD screen and the OLED screen are inconsistent is solved by adopting the scaling interpolation unit based on the RAM cache in the FPGA, high flexibility and adaptability are achieved, the system guarantees the quality and integrity of images through accurate interpolation calculation and scaling processing, the visual experience is improved, and the system is suitable for popularization and application. And the user can fully utilize the advantage of high resolution of the OLED screen after replacing the screen, and meanwhile, the problems of image deformation, blurring or incomplete display and the like possibly caused by mismatching of the resolution are avoided.
Owner:SHENZHEN MOORECHIP TECH CO LTD

Binocular display adjustment and FOV consistency compensation method and device for NED equipment

The present application belongs to the field of near-eye display, and specifically discloses a binocular display adjustment and FOV consistency compensation method and device for NED devices. The display adjustment method includes: respectively obtaining the FOV and display resolution of two optical display systems; when the two FOVs are inconsistent, determining the target FOV; the target FOV is less than or equal to any one of the two FOVs; according to the target FOV, the two FOVs and the two display resolutions, respectively determining the display resolution adjustment values ​​of the two optical display systems; wherein the ratio of the display resolution adjustment value to the display resolution of each optical display system is equal to the ratio of the target FOV to the FOV of the corresponding optical display system; if the display resolution adjustment value is less than its display resolution, the size of the picture to be displayed by the optical display system is interpolated according to the display resolution adjustment value, so that the optical display system displays the picture after the size interpolation. Through the present application, the consistency compensation of the binocular FOV of the NED device can be achieved.
Owner:WUHAN JINGLI ELECTRONICS TECH +1

Geocoding-based investment attraction map drawing method, system and equipment and medium

The invention provides a geographic coding-based investment attraction map drawing method, system and device and a medium, and belongs to the technical field of map drawing, the method comprises the following steps: establishing an enterprise library for an investment attraction area, and carrying out geographic coding on an enterprise address in enterprise information in the enterprise library to obtain an enterprise geographic coordinate; performing address analysis and aggregation on enterprise addresses in the enterprise information to obtain administrative division codes of each level of a region to which an enterprise belongs; performing enterprise information summarization of each level on the administrative division code of each level of the investment attraction area, and storing a summarizing result; and in response to the hierarchical display request of the user, rendering the enterprise information summarized at the corresponding hierarchy for the investment attraction map, and in response to the enterprise display request of the user under the lowest hierarchical display request, performing enterprise position rendering according to the enterprise geographic coordinates. According to the method, through automatic address coordinate conversion and map drawing, the drawing efficiency of the investment attraction map is improved, and the accuracy of the enterprise position is ensured by utilizing the geocoding service.
Owner:INSPUR YUNZHOU (SHANDONG) IND INTERNET CO LTD

A method, system and storage medium for adaptive recognition of multi-source heterogeneous data collection

ActiveCN114358079Bresolve differencesImprove efficiencyData classAdaptive identification
The present invention relates to a method, system and storage medium for adaptive recognition of multi-source heterogeneous data collection. The method comprises: monitoring the real-time status of a front-end module; generating configuration status information according to the real-time status of the front-end module; adjusting configuration parameters according to the configuration status information; and configuring corresponding modes according to the configuration parameters. The present invention realizes adaptive recognition according to different types of front-end acquisition data, greatly improving efficiency and saving costs.
Owner:硕橙(厦门)科技有限公司

Anomaly detection method and device for planar geographic entities

The present invention provides an anomaly detection method and device for planar geographic entities. The method comprises: constructing and training a fused semantic segmentation model including at least two fused semantic segmentation models set in parallel and using an additive fusion method to fuse the prediction results of each fused semantic segmentation model as a classification prediction result; constructing and training a fused change detection model including at least two change detection models set in parallel and using an additive fusion method to fuse the prediction results of each change detection model as a change prediction result; acquiring image data of a to-be-detected area and planar geographic entity data to be detected, obtaining a to-be-detected data set and a land class label set; inputting the to-be-detected data set into the fused semantic segmentation model and the fused change detection model, obtaining a classification prediction result and a change prediction result; using the classification prediction result to assign category attributes to the change prediction result, obtaining a fused prediction result; and comparing the fused prediction result with the elements with the same name in the land class label set.
Owner:SICHUAN SURVEYING & MAPPING PROD QUALITY SUPERVISION & INSPECTION STATION OF THE MINIST OF NATURAL RESOURCES SICHUAN SURVEYING & MAPPING PROD QUALITY SUPERVISION & INSPECTION STATION +1

WEB application firewall automatic test method and device based on distributed scheduling mechanism

The invention provides a WEB application firewall automatic test method and device based on a distributed scheduling mechanism, and the method comprises the steps: enabling a host process to access a preset number of protection websites based on a one-host multi-slave structure of the distributed scheduling mechanism; collecting test cases, and grouping the test cases by the host process; the sub-process is initialized, and the main process distributes the test cases of different groups to work nodes with the same number as the protection websites; the working nodes execute the test cases in parallel, execute the test cases after receiving the test cases sent by the host process, and report test results to the host process; the host process collects a test result; according to the method, the test cases are executed in parallel through a distributed scheduling mechanism, the whole process work is automatically set, the human input of the test is saved to the maximum extent, and the problems that the case construction efficiency is low, and the test efficiency is high are solved. And whether an existing protection module can protect vulnerabilities or not cannot be checked in time.
Owner:CHINA TELECOM CLOUD TECH CO LTD

A template matching method based on a twin network and accurate center point positioning

The present application belongs to the technical field of image processing, and particularly relates to a template matching method based on a twin network and accurate center point positioning. The method comprises the following steps: S1, obtaining a training data set, i.e. a template and a search image; S2, constructing a template matching network based on a twin network and accurate center point positioning, and inputting the training data set of S1 into the template matching network, wherein the template matching network is composed of three parts, i.e. a twin feature extraction network, a dynamic shrink cross-correlation network and a center point positioning network, which are sequentially cascaded; and S3, training the template matching network of S2 by using a loss function. The method can better solve the problem of differences between the template and the search image, effectively improve the positioning accuracy of the target center point and the robustness of the template matching.
Owner:NAT UNIV OF DEFENSE TECH

Privileged account management and control method and device based on database limited query

The embodiment of the invention discloses a privileged account management and control method and device based on database limited query, and the method comprises the steps: configuring drive connection information through a business configuration interface, and configuring a privileged user and a control strategy of a to-be-looked-up table through a strategy controller configuration interface; the PIM JDBC driving program package analyzes the to-be-analyzed statement by using a grammar analyzer to generate a syntax tree, judges whether a clause belonging to a sub-query or a first-level query exists in the to-be-analyzed statement or not, and obtains an actual table name of a to-be-looked-up table in a database; and starting a filtering condition set in the control strategy of the privileged account so as to release, prohibit or limit query of the to-be-looked-up table by using the actual table name of the to-be-looked-up table in the database, and filtering a query result. According to the technical scheme of the invention, security threats such as privilege exceeding use, privilege abuse, abnormal access, illegal operation and the like can be avoided.
Owner:AVICIT CO LTD

Automatic positioning tool switching equipment for measurement and inspection of machined products

The invention discloses automatic positioning tool switching equipment for measurement and inspection of machined products, and the equipment is provided with a tool switching shift-out system, so that the problems of a non-standard positioning base and a specific positioning mechanism can be avoided, the switching of a manual positioning mechanism during the switching of line products is avoided, and the production efficiency is improved. The position precision of the positioning mechanism needs to be repeatedly switched and adjusted according to different products; due to the arrangement of the product tool positioning system, the problem of differences among different product tool positioning systems is solved, the difference tolerance of multiple accessory devices is reduced, and the product quality of a wire body is improved; the switching position, the positioning structure and the working position of the product tool positioning system do not interfere with one another, line body production and product positioning tool same-beat synchronous switching are achieved, and the line body production efficiency is improved. Finally, on the premise that the product positioning tool system meets the positioning precision requirement, according to the line body production scheduling plan, lossless switching of the product positioning tool system is achieved, stable productivity output of the line body is provided, and the line body starting rate is increased.
Owner:XIAOAO IND INTELLIGENT EQUIP (SUZHOU) CO LTD +1

Consistent semi-supervised pericardial fat segmentation method based on difference guidance

The invention belongs to the technical field of medical image segmentation, and particularly relates to a consistency semi-supervised pericardial fat segmentation method based on difference guidance. Firstly, a data set is acquired and processed; then, replacing VSS blocks of the Mamb-Unet network one by one by using MCM blocks, and further obtaining a teacher model and a student model; in an MCM block, an input tensor is firstly equally divided into two tensors # imgabs0 # and # imgabs1 # in a channel dimension; after the tensor # imgabs2 # is sequentially subjected to convolution, activation and convolution and activation operation, the tensor # imgabs2 # and the tensor # imgabs2 # are subjected to jump connection, and a tensor # imgabs3 # is obtained; processing the tensor # imgabs4 # through two information flow branches to obtain a tensor # imgabs5 #; the tensor # imgabs6 # and the tensor # imgabs7 # are spliced and subjected to convolution, and then jump connection is carried out on the tensor # imgabs6 # and the tensor # imgabs7 # and the input tensor in the MCM block to obtain the output tensor of the MCM block; and finally, performing semi-supervised training on the collaborative mean teacher model based on difference fusion, and using the trained teacher model as a segmentation model for segmentation of pericardial fat. The model pays more attention to fuzzy regions and boundary information of pericardial fat, and the segmentation precision is improved.
Owner:HEBEI UNIV OF TECH

Multi-modal image fusion method and system based on inverse diffusion model, device and readable storage medium

ActiveCN120070202BPreserve text interactivityFlexible control of intensityImage enhancementInternal combustion piston enginesData domainComputational physics
The present application relates to a kind of multimodal image fusion methods of inverse diffusion model, comprising the following steps: step one, using inverse diffusion technology, visible light image is reversed to noise latent space, then using the feature of reversed visible light image, guide infrared image is reversed;Step two, guide by the inverse process in diffusion model, inject the appearance attribute of visible light into infrared feature, and the feature can generate infrared image with visible light style;Step three, design specific fusion rule, for the attention layer fusion of denoising process, reversed visible light and infrared feature are fused, the text interaction capability of model is retained, and language-driven fusion control is supported.The present application can directly generate high-quality fusion image without additional training or fine-tuning.The obtained fusion image is highly compatible with the base model, effectively solves the difference problem between data domains, and significantly improves the performance of downstream machine perception tasks.The present application significantly reduces the training cost, and provides an efficient and innovative solution for cross-domain tasks.
Owner:HARBIN INST OF TECH

Ground station alignment and pattern generation method and system

ActiveCN122226127BSolve the problem of beam pointingSolve the problem of design value deviation
The application discloses a ground station and satellite link alignment and pattern generation method and system, wherein the method comprises the following steps: acquiring a radiation power threshold of a ground transmitting source and determining a satellite position reference signal, and converting to a ground coordinate system to obtain preliminary pointing parameters. Based on the preliminary pointing parameters, a servo mechanism is driven to scan and search for an angle position corresponding to a maximum receiving level, accurate pointing coordinates are determined, and the ground transmitting source beam is accurately pointed to the satellite. In the state that the ground transmitting source beam is accurately pointed to the satellite, the radiometer pointing angle in the satellite platform coordinate system is determined according to the geographical position information of the ground transmitting source, the satellite-borne radiometer beam is driven to search and adjust, the satellite position is locked, and initial alignment data of the space-earth link are acquired. The radiometer scanning range is extracted from the initial alignment data of the space-earth link, and the radiometer beam is driven to perform search scanning. Therefore, the application improves the accuracy of in-orbit antenna performance evaluation.
Owner:NAT SATELLITE METEOROLOGICAL CENT

Excel report data and system data matching settlement processing method, system and equipment and storage medium

The invention relates to the technical field of data processing, in particular to an Excel report data and system data matching settlement processing method, system and device and a storage medium. According to the method, a unified field format model is constructed by obtaining template configuration content including a field format rule, a header mapping rule and a matching field rule, and header identification, field mapping and format normalization processing are performed on an Excel report to obtain standardized report data. And generating a unique matching identifier based on the matching field rule, comparing the unique matching identifier with the system data one by one to obtain a matching result, and generating a standard identifier according to a standard condition. Further performing question marking on the unmatched or abnormal records to form question records, and finally generating a settlement processing report based on the matching result, the standard mark and the question records. According to the invention, accurate matching and abnormity pre-recognition of report data and system data are realized, and the accuracy, efficiency and traceability of settlement processing are improved.
Owner:GUANGDONG WANZHANG JINSHU INFORMATION TECH CO LTD

Thermal barrier coating heat insulation effect test method based on ITO-AZO film thermocouple

The invention provides a thermal barrier coating heat insulation effect test method based on an ITO-AZO thin film thermocouple. The thermal barrier coating heat insulation effect test method comprises the following steps of preparing an insulating layer, preparing a lower-layer thin film thermocouple, preparing a thermal barrier coating, preparing an upper-layer thin film thermocouple and testing the heat insulation effect of the thermal barrier coating. The evaluation of the thermal barrier coating in the flow field environment of 1200 DEG C or below is realized by preparing the double-layer ITO-AZO film thermocouple on the surface of the turbine blade.
Owner:AVIC BEIJING INST OF AERONAUTICAL MATERIALS

Method and device for processing photovoltaic IV data, electronic equipment and storage medium

The application provides a photovoltaic IV data processing method and device, electronic equipment and storage medium. The method comprises the following steps: acquiring IV data obtained by scanning a target photovoltaic module in a target period; performing normalization processing on the IV data according to one of at least one preset normalization mode; the at least one preset normalization mode comprises a normalization mode based on a selected standard IV curve of the target photovoltaic module; wherein the selected standard IV curve is a standard IV curve of the target photovoltaic module corresponding to the irradiance value of the target period corrected by a preset correction mode, and the preset correction mode is a correction mode for correcting the irradiance value collected by an irradiance meter according to the angle parameter of the target photovoltaic module. The application can improve the diagnosis effect of the photovoltaic module.
Owner:XIAMEN KEHUA DIGITAL ENERGY TECH CO LTD

Escalator multi-source heterogeneous quality detection report generation method

The invention discloses an escalator multi-source heterogeneous quality detection report generation method, which comprises the following steps that S1, quality detection information of an escalator is collected from a plurality of heterogeneous data sources, and the quality detection information contains diversity data of different types and formats; s2, compiling the quality detection information from each data source into a uniform data format for data integration, solving the difference and inconsistency among heterogeneous data, and forming a uniform data view; s3, performing analysis and anomaly prediction on the integrated data by using a data analysis and model algorithm to obtain a quality evaluation result; and S4, based on the quality evaluation result, a quality detection report is generated, and the quality detection report comprises various quality index data, a trend chart and an anomaly detection result. According to the method, the efficiency and accuracy of quality detection are improved, the quality detection report can be quickly, accurately and comprehensively generated, and comprehensive monitoring and timely maintenance of the running state of the system are realized.
Owner:XIAMEN JIANHUI INFORMATION TECH CO LTD

Soil covering device for cultivation of interplanting of sugarcane and tartary buckwheat

The invention discloses a soil covering device for sugarcane interplanting tartary buckwheat cultivation, and relates to the technical field of soil covering, the soil covering device comprises a soil covering machine body, the soil covering machine body is fixedly connected with a soil covering cover, the lower portion of the soil covering cover is fixedly connected with first inclined plates symmetrically distributed along the soil covering cover, and the first inclined plates are fixedly connected with second inclined plates symmetrically distributed along the soil covering cover. The lower portion of the soil covering cover is fixedly connected with second inclined plates symmetrically distributed along the soil covering cover, a first discharging port is formed between every two adjacent second inclined plates, a second discharging port is formed between every two adjacent first inclined plates and second inclined plates, and a screen shoe is fixedly connected between every two adjacent first inclined plates and second inclined plates. According to the sugarcane and tartary buckwheat interplanting device, shunting of covering soil is controlled through the screen frame, so that more covering soil is obtained for sugarcane seeds, less covering soil is obtained for buckwheat seeds, the problem of covering soil difference during sugarcane and tartary buckwheat interplanting cultivation is solved, the field management difficulty is reduced, and the overall planting effect is improved.
Owner:CHENZHOU QINTIAN AGRICULTURAL TECHNOLOGY CO LTD

Correction method, device and equipment for gear stepless speed regulation system and storage medium

PendingCN119102899AEnsure accurate tuningSmall speed errorElectrical controlMachines/enginesDiesel locomotiveBench test
The invention provides a correction method, device and equipment for a gear stepless speed regulation system and a storage medium, and relates to the technical field of diesel engines. The method is applied to a diesel locomotive in a bench test stage, and comprises the following steps: acquiring a rotating speed error of a diesel engine; wherein the rotating speed error is determined according to the actual rotating speed and the expected rotating speed of the diesel engine; when the rotating speed error is out of the first preset interval, a control pulse signal of a driver of the gear stepless speed regulation system is adjusted to adjust the rotating speed error until the adjusted rotating speed error is within a second preset interval; wherein the second preset interval is a subset or equal set of the first preset interval; and according to an adjustment result of the control pulse signal, obtaining a correction parameter of the driver, and according to the correction parameter, correcting the driver in an actual use stage of the diesel locomotive. The problem of how to correct the gear stepless speed regulation system to reduce the rotating speed error when the rotating speed error is relatively high is solved.
Owner:CNR LANZHOU LOCOMOTIVE

Traffic control agent question and answer method and system based on Text2SQL

The invention relates to the technical field of intelligent traffic management and natural language processing, and discloses a Text2SQL-based traffic control agent question and answer method and system, and the method comprises the steps: obtaining a natural language query inputted by a user, and extracting at least one query condition from the natural language query; matching the at least one query condition with a preset vector database, and converting the query condition into a standard term in the field of traffic control; based on the standard terms and preset database table structure information, utilizing a large language model to execute Text2SQL conversion, and generating corresponding SQL query statements; and obtaining a query result from the traffic control database according to the SQL query statement and outputting the query result. According to the method and the device, the problems that the preset template cannot cover complex business requirements, the general large model field is misused and logic deviation is caused are solved, and the query accuracy and expandability in the traffic control field are improved.
Owner:BEIJING SINOITS TECH

Video auxiliary analysis system and method based on artificial intelligence

The invention relates to the technical field of video auxiliary analysis, in particular to a video auxiliary analysis system and method based on artificial intelligence. The invention discloses a video auxiliary analysis method based on artificial intelligence, and the method comprises the steps: 1, carrying out the ultrasonic scanning of a to-be-detected person through an ultrasonic robot, and obtaining an original ultrasonic image; calculating fuzzy pixel detail loss and structure detail loss in the original ultrasonic image to obtain a fine processing ultrasonic image; acquiring a video acquired by the ultrasonic probe in the fine processing ultrasonic image and a scanning track of the ultrasonic probe; and 2, carrying out data recording on a scanning process based on a human body digital twin model, and realizing autonomous ultrasonic scanning through a scanning thought decision maker and a video auxiliary analysis module. According to the method, the image segmentation result is evaluated in a unified manner by calculating the fuzzy pixel detail loss and the structure detail loss in the original ultrasonic image, and the accuracy and definition of the original ultrasonic image used for follow-up video auxiliary analysis are improved.
Owner:HUA PING XIANGSHENG (SHANGHAI) MEDICAL TECH CO LTD