Patents
Literature
29results about How to "Reduced ability to recognize" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Sign language translation method and device based on large language model
PendingCN121768069AReduce computing power requirementsEffective filteringCharacter and pattern recognitionBiological modelsPattern recognitionFrame (artificial intelligence)
The invention belongs to the crossing field of artificial intelligence and barrier-free assistance technology, and particularly discloses a sign language translation method and device based on a large language model.The method is applied to a terminal and comprises the steps that key points are extracted from sign language video frames; based on the coordinates, types and global indexes of the key points in the sign language video frames, obtaining fusion features through feature fusion; based on the fusion features corresponding to the sign language video frames in the frame window, time sequence modeling and classification are carried out, and a word prediction result of the frame window is obtained; a sliding window voting and deduplication mode is adopted, the candidate word sequence is preprocessed, a preprocessed word sequence is obtained, and the candidate word sequence is formed by connecting word prediction results of all frame windows in series according to a time sequence; based on the preprocessed word sequence, word error correction and statement generation are carried out by calling a large language model, and a sign language translation result is generated. According to the invention, sign language video translation can be realized for the terminal, and the accuracy and fluency of the translation result can be guaranteed.
Owner:SOUTH CENTRAL UNIVERSITY FOR NATIONALITIES
Antibacterial neural electrode based on high surface potential zirconium oxide layer and preparation method thereof
The application provides an antibacterial neural electrode based on a high-surface-potential zirconium oxide layer and a preparation method thereof. The electrode comprises, from bottom to top, a bottom zirconium oxide film layer, a first insulating layer, a metal layer, a second insulating layer, a top zirconium oxide film layer and an electrode modification layer. A distal end of the metal layer is partially exposed to form an electrode point, and the electrode modification layer covers the electrode point. The bottom zirconium oxide film layer and the top zirconium oxide film layer are subjected to high-surface-potential treatment and exhibit a positive surface potential in a physiological environment. The positive surface potential can destroy the cell membranes of bacteria with negative charges through electrostatic action after the neural electrode is implanted in vivo, and inhibit the formation of microglial cells and astrocytes. The damage to the membranes of mammalian cells (such as neurons) with neutral electricity is extremely small. The application realizes active antibacterial function through the high-surface-potential zirconium oxide film layer, ensures long-term effective contact between the electrode and neurons, and thus realizes high-quality, long-term stable electrophysiological recording and stimulation function of the neural electrode.
Owner:SHANGHAI JIAOTONG UNIV
Structured processing method and device of software engineering elements, electronic equipment and medium
ActiveCN121455449BReduced ability to recognizereduce workloadVersion controlRequirement analysisSoftware engineeringSoftware development
This application provides a structured processing method, apparatus, electronic device, and medium for software engineering elements, relating to the field of software development technology. The method includes: generating an engineering element table for multiple types of software engineering objects for a preset software engineering project; each engineering element in the table records an element identifier and basic attribute information of the engineering element in the software engineering object; constructing an element reference chain based on the relationships between multiple engineering elements and element identifiers; the element reference chain consisting of at least a source element identifier, a target element identifier, and a relationship type; responding to a change event for a first engineering element, determining the affected engineering element based on the element identifier and element reference chain of the first engineering element; and verifying the affected engineering element based on a verification list generated for the affected engineering element. This application can determine affected engineering elements based on unified engineering elements and element reference chains, improving the efficiency of software development and version release.
Owner:YUDONGYUAN (BEIJING) INFORMATION TECH CO LTD
Human-computer voice interaction method and device, storage medium and electronic device
PendingCN122266348Aimprove accuracyImprove real-time performanceSpeech recognitionEngineeringAutomatic speech
The application discloses a human-computer voice interaction method and device, a storage medium and an electronic device, relates to the technical field of smart homes, and comprises the following steps: automatically performing voice recognition on voice interaction information of a target object, obtaining a first intermediate recognition text and a second intermediate recognition text, a pause duration threshold set in a first voice activity detection strategy for detecting a moment when the target object stops speaking is lower than a pause duration threshold set in a second voice activity detection strategy for detecting the moment when the target object stops speaking; comparing the first intermediate recognition text and the second intermediate recognition text until the second intermediate recognition text is consistent with the first intermediate recognition text, obtaining a target recognition result of the voice interaction information based on a voice recognition end identifier of the monitored voice interaction information; and performing natural language processing on the target recognition result to obtain a first interaction intention, thereby solving the technical problem that automatic voice recognition is not accurate enough in the human-computer voice interaction process.
Owner:HAIER YOUJIA INTELLIGENT TECH (BEIJING) CO LTD
Computer flat cable automatic detection device
ActiveCN224287024UIncrease the level of automationreduce coverageElectrical testingMeasurement instrument housingSoftware engineeringRibbon cable
The utility model discloses a computer flat cable automatic detection device, and relates to the technical field of computer detection equipment. The utility model discloses an automatic detection device for a computer flat cable, and the device comprises a detection platform which is used for installing a to-be-detected computer; the number of the supporting columns is four, the four supporting columns are distributed on the outer edge of the detection table in a rectangular array mode, and a mounting table is arranged at the free ends of the supporting columns; the detection assembly is installed on the installation table, the detection assembly is right opposite to the table top of the detection table, and the detection assembly is used for detecting a to-be-detected computer; wherein a detection channel is arranged between every two adjacent supporting columns.
Owner:XINXIWANG INTELLIGENT TECH (SHENZHEN) CO LTD
Metabolism-enhanced anti-tumor car-m cells co-expressing slc proteins, construction method and application thereof
PendingCN122081236Aimprove securityimprove featuresImmunoglobulins against cell receptors/antigens/surface-determinantsFermentationAntigen bindingTumor specific
This invention discloses a metabolically enhanced anti-tumor CAR-M cell co-expressing SLC protein, comprising the nucleotide sequence encoding the HER2 antigen-binding domain scFv and the nucleotide sequence encoding the SLC protein. The invention also discloses a method for constructing the aforementioned anti-tumor CAR-M cell and its application in the preparation of anti-tumor drugs. The anti-tumor CAR-M cell of this invention specifically recognizes HER2, thereby effectively reducing off-target toxicity, improving treatment safety and tumor specificity, and exhibiting significantly enhanced glutamine uptake capacity. It possesses a good metabolic reprogramming effect at the molecular level, resulting in stronger anti-tumor activity due to enhanced metabolism.
Owner:SUN YAT SEN UNIV +2
Intelligent homework correcting method based on geometric proof question
PendingCN121963240Aaccurate identificationHandle diversity efficientlySemantic analysisCharacter and pattern recognitionGraphicsStructure analysis
The invention provides an intelligent homework correcting method based on geometric proof questions. The intelligent homework correcting method comprises a question image analysis step, a reference answer structured analysis step, a student answer semantic normalization step and a proof path matching judgment step. According to the method, a user-defined corner name in a student graphic label is efficiently and accurately analyzed, angle semantic expression is unified, structured analysis is carried out on a student written proof text, and a logic derivation path is extracted, so that whether an effective reasoning chain from question condition derivation to conclusion is formed or not is judged; and the understanding ability of custom labels of students and the structured judgment ability of logical reasoning chains are obviously improved.
Owner:BEIJING NORMAL UNIV AT ZHUHAI
Target object recognition method, device, and storage medium
PendingCN122290001AReduced ability to recognizeReduce recognition distancePattern recognitionComputer graphics (images)
This application provides a method, apparatus, device, and storage medium for identifying a target object, relating to the field of video processing technology. The method includes: when identifying a target object, first acquiring video frame images of the target object captured by a vision device, and simultaneously detecting the position of the target object by a radar device; and based on the position of the target object, determining the target image region where the target object is located from the video frame images; based on the target image region, extracting a portion of the video frame images containing the target object; and then identifying the target object in the portion of the video frame images to obtain the identification result of the target object. Using the technical solution of this application, the accuracy of the identification result can be improved without being limited by computing power.
Owner:ZHEJIANG UNIVIEW TECH CO LTD
Live broadcast interactive information display method, processing method, device and equipment
PendingCN121888010AImprove live streaming experienceReduce the probability of misuseSelective content distributionGraphical user interfaceThe Internet
The invention provides a live broadcast interactive information display method, processing method, device and equipment, and relates to the technical field of Internet live broadcast. The live broadcast interaction information display method in the disclosure comprises the steps of displaying reminding information based on a graphical user interface, the reminding information being generated based on interaction information of a live broadcast room; obtaining an interactive operation of the graphical user interface, wherein the interactive operation comprises a touch operation or a click operation; and determining the display position of the reminding information based on the distribution condition of the interactive operation in the graphical user interface.
Owner:SHANGHAI BILIBILI TECH CO LTD
A method and system for acute large vessel occlusion identification and reperfusion decision making
PendingCN122117322AReduced ability to recognizeshorten the timeMedical data miningMedical automated diagnosisBlood vessel occlusionMedical record
The application discloses an acute large blood vessel occlusion identification and reperfusion decision method and system, and the method comprises the following steps: S1, obtaining medical record text and head multi-modal CT image data of a patient to be diagnosed; S2, performing natural language processing on the medical record text to obtain text features; S3, processing the multi-modal CT image data, calculating the ASPECTS score of non-enhanced CT, and positioning the blood vessel occlusion position and evaluating the collateral circulation from the CTA image to obtain image features; S4, performing weighted fusion on the text features and the image features to generate fusion features; and S5, inputting the fusion features into a pre-constructed guideline knowledge graph and a decision model to generate an individualized acute large blood vessel occlusion identification result and a reperfusion treatment suggestion. The application can automatically, quickly and accurately generate an individualized identification result and a treatment suggestion by fusing the features of the medical record text and the multi-modal CT image and combining a real-time updated guideline knowledge graph.
Owner:BEIJING TSINGHUA CHANGGUNG HOSPITAL
A multi-modal feature fusion water area target detection method
ActiveCN121392252Baccurate focusEliminate global driftCharacter and pattern recognitionPattern recognitionRgb image
This invention belongs to the field of target detection technology, specifically relating to a multimodal feature fusion method for water target detection. The method includes the following steps in sequence: a preprocessing step, including: based on two adjacent RGB image frames as input, separating mirror perturbations to generate a mirror mask and a motion cue map; an alignment and fusion step, including: using a stable frame as the primary modality and the mirror mask and motion cue map as secondary modalities, extracting primary and secondary modal features; and inputting the fused features into a detection head to obtain initial candidate boxes and category scores; and a loop closure determination step, including: based on the conformal saliency ratio calculated for the initial candidate boxes and calibrated within the same frame, outputting the final detection result for that frame. This invention can automatically identify and eliminate unstable candidates caused by reflection. It also enhances the robustness and consistency of the model in complex scenes such as strong reflections, water wave disturbances, and changes in viewing angle.
Owner:LIAOCHENG UNIV
Face recognition terminal
ActiveCN224188316UEasily complete face recognition operationsImprove versatilityStands/trestlesStructural engineeringMechanical engineering
Owner:HANGZHOU XINMINGYE INFORMATION TECHNOLOGY CO LTD
Face recognition method based on point cloud data and RGB image sequential verification
PendingCN121963275Areliable renderingconsistent threshold systemCharacter and pattern recognitionBiological modelsFace detectionVoxel
The invention provides a face recognition method based on point cloud data and RGB image sequential verification, and the method comprises the following steps: collecting two types of data at the same time, completing the face detection and cutting of an RGB image, combining histogram equalization and illumination compensation, extracting unitized features, comparing the unitized features with a feature library, and carrying out the confidence calibration. And according to the first upper threshold value and the first lower threshold value, primary judgment of passing, re-verification or refusal is made. After the RGB image passes verification, selecting a point cloud corresponding to a human face region, executing voxel downsampling, counting abnormal point removal and normal estimation, calculating local geometric description, performing robust registration, and constructing a single geometric similarity index based on a median absolute deviation of a point-to-surface residual error and quantile statistics; and outputting passing, re-checking or refusing according to the second upper threshold value and the second lower threshold value. Only when the two stages pass, an identity conclusion and confidence information are given; and when any stage is not passed or re-verification is not passed, outputting a rejection result or triggering a warning or auxiliary verification.
Owner:ZHEJIANG UNIV OF SCI & TECH
Duodenoscope system, duodenoscope system control method and storage medium
The invention relates to the technical field of endoscopes, and discloses a duodenoscope system, a duodenoscope system control method and a storage medium. The duodenoscope system comprises a foresight camera module used for outputting illumination light for illumination and collecting a foresight image in the lens entering process; the side view camera module is used for outputting light of a target wave band to irradiate a target area and collecting an image of the target area in the treatment process; and the processor is used for controlling the front-view camera module and the side-view camera module to output light rays and outputting a front-view image or the target area image. The foresight camera module can realize illumination and image acquisition in the lens entering process, so that the convenience of a doctor in lens entering operation is improved; the side-view camera module can output light of a target wave band to irradiate a target area and collect an image of the target area, so that a doctor can quickly determine target tissue; the difference between operation and image recognition of different doctors on the duodenoscope system is reduced, and the overall medical quality is improved.
Owner:SHENZHEN CONCEMED MEDICAL TECHNOLOGY CO LTD
A multi-source heterogeneous data processing method and system for business security monitoring
The application relates to the technical field of data processing, and discloses a multi-source heterogeneous data processing method and system for business security monitoring, which comprises the following steps: collecting original business data to perform feature extraction and obtain current structural features; comparing the current structural features with historical structural features, and performing drift determination in combination with the hit change of a preset paradigm field; when the field splitting drifts, performing field reorganization processing on the original business data to obtain normalized semantic values; generating stable alternative identifiers according to the normalized semantic values, and forming new mapping results and historical mapping results; performing parallel verification on the new mapping results and the historical mapping results to obtain verification results; when the verification results meet preset switching conditions, outputting target paradigm data, and using the target paradigm data for business security monitoring. The application improves the normalization processing stability of multi-source heterogeneous business data, the business object continuous association capability and the business security monitoring accuracy in a structural change scenario.
Owner:CHINA INT DATA SYST CO LTD
Data center inspection system, battery anomaly identification method, device, and storage medium
ActiveCN114943858BImprove anomaly identification efficiencyAvoid missing exceptionsCharacter and pattern recognitionSecondary cells servicing/maintenanceElectrical batteryData center
Embodiments of the present application provide a data center inspection system, a battery anomaly identification method, equipment and a storage medium. In the embodiments of the present application, a battery array image of a data center collected by a self-moving device can be obtained; and battery features of the battery array image are extracted to obtain battery features reflected by the battery array image; then, according to the battery features reflected by the battery array image, an abnormal battery in a target battery included in the battery array image and a target abnormal type of the abnormal battery can be identified, so as to realize automatic identification of the abnormal battery and the battery abnormal type of the abnormal battery, which helps to improve the battery anomaly identification efficiency compared with the manual inspection mode. On the other hand, compared with the manual inspection mode, the battery anomaly missed detection and misidentification caused by insufficient experience or negligence of the manual inspection can be avoided, which helps to reduce the probability of the battery anomaly missed detection and the probability of the misidentification.
Owner:ALIBABA (CHINA) CO LTD
Credit entry method based on smart contract and terminal device
The application relates to the technical field of credit entry, in particular to a credit entry method and terminal equipment based on a smart contract, which comprises the following steps: S1, uploading credit proof materials, performing feature rough extraction on the credit proof materials to obtain rough recognition results; S2, matching the rough recognition results based on a preset certificate template library to extract key recognition results; S3, matching the key recognition results based on a smart contract deployed on a blockchain to obtain credit values; S4, performing hash calculation on the credit proof materials to obtain material hash values, and performing blockchain storage on the credit values and the corresponding material hash values to complete credit entry. Through the whole-process processing of credit material uploading, key information recognition and credit calculation to blockchain storage, the artificial input and time cost are greatly reduced, the efficiency, digitization and intelligentization of credit entry management are effectively improved, and the technical effect that the material storage is unalterable is achieved.
Owner:国网浙江省电力有限公司新昌县供电公司
Data anomaly adaptive detection intelligent early warning method based on edge calculation
PendingCN121959335AMeet real-time processing requirementsPrecise anomaly identificationNeural learning methodsRegression analysisEdge computing
The invention provides a data anomaly adaptive detection intelligent early warning method based on edge calculation. The method comprises the following steps: S1, acquiring monitoring data; s2, performing regression analysis, and determining tendency; s3, if the trend exists, judging abnormity based on the LSTM; s4, if the data does not have the tendency, judging whether the data accords with bimodal distribution based on K-means clustering, and if the data accords with the bimodal distribution, judging that the data is abnormal based on a K-means clustering result; s5, if no tendency exists and no bimodal distribution exists, judging abnormity based on LSTM and box diagram analysis; s6, correcting a normal value or retaining a preliminary abnormal value; s7, judging the abnormal value as a real abnormal value; and S8, outputting an equipment fault early warning signal or a normal monitoring signal according to a result of the S7. According to the method, the limitation that only known data change rules can be processed in the prior art is overcome, the adaptability to variable environments is enhanced, and a solid technical support is provided for stable operation and timely fault early warning of Internet of Things equipment.
Owner:SHANGHAI URBAN INVESTMENT SMART WATER DEVELOPMENT CO LTD
A method for anti-buoyancy reinforcement of shield tunnels spanning utility tunnels in water-rich silty sand strata
ActiveCN121167833BAchieve continuous refined modelingImprove reliabilityGeometric CADDesign optimisation/simulationSoil scienceStructural engineering
This invention discloses a method for anti-buoyancy reinforcement of shield tunnels spanning utility tunnels in water-rich silty sand strata, comprising: obtaining a stratum distribution model based on three-dimensional geological data of the water-rich silty sand strata; obtaining disaster sign activation signals based on the stratum distribution model; obtaining preliminary layout parameters of the defense barrier based on the disaster sign activation signals; obtaining a drainage joint scheme based on the preliminary layout parameters of the defense barrier; obtaining a spatial composition network based on the drainage joint scheme; obtaining optimization iteration results based on the spatial composition network; obtaining construction sequence data based on the optimization iteration results; and obtaining the final stability mitigation index based on the construction sequence data. This invention can significantly improve the anti-buoyancy stability and construction safety of utility tunnels in water-rich silty sand strata, providing efficient and replicable technical support for disaster prevention and control in underground engineering under complex geological conditions.
Owner:CCCC THIRD HIGHWAY ENG CO LTD
Intelligent programmable control cabinet and VOC exhaust emission system
ActiveCN224401858UUniform clamping forceprevent slippageCircuit arrangements on support structuresSupport structure mountingSlide plateControl theory
The utility model discloses an intelligent programmable control cabinet and V0C waste gas discharging system relates to the technical field of control cabinet, aims at solving the technical problem that traditional control cabinet direct connection type wiring makes the wire exposed to the risk of external force interference, including control cabinet body, bundling mechanism and winding mechanism. The utility model discloses through the rubber pad through the slide and spring connection, when the cable is pressed into between the rubber pad, spring can follow the cable diameter self -adaptation telescoping, simultaneously, the rotation rod passes through the connecting rod synchronous drive both sides slide plate movement, ensure that both sides rubber pad to cable exert even clamping force, adapt the fixed demand of different diameter cable. In addition, the rubber pad inboard's multiple groups reverse barb and S shape cable channel cooperation, barb can embed cable surface, both avoid cable to slip, and through S shape path increase cable and rubber pad's friction, further improve the fixed stability, solve the problem that traditional control cabinet direct connection type wiring makes the wire exposed to the risk of external force interference.
Owner:施朗智能科技(江苏)有限公司
Warehouse business compliance verification method and device, computer device, storage medium and computer program product
This application relates to a method, apparatus, computer equipment, storage medium, and computer program product for compliance verification of warehousing operations. It pertains to the field of compliance verification technology. The method includes: acquiring multi-source warehousing business data under the warehousing business scenario to be verified; inputting the multi-source warehousing business data into a pre-built warehousing business compliance verification knowledge graph for graph matching to obtain a matching result; the matching result includes warehousing business entity information, warehousing business attribute information, and warehousing business association information corresponding to the multi-source warehousing business data; inputting the matching result into a pre-built warehousing business compliance rule base for compliance verification to obtain a compliance verification result for the multi-source warehousing business data; wherein, the pre-built warehousing business compliance rule base is determined based on a pre-built warehousing business compliance verification knowledge graph. This method can improve the efficiency and accuracy of warehousing business compliance verification.
Owner:CHINA TOBACCO SICHUAN IND CO LTD
Fire hazard identification method and system based on image enhancement
ActiveCN121366334BReduced ability to recognizeReduce false alarm rateImage enhancementImage analysisEngineeringThresholding
The present application relates to the technical field of fire monitoring, in particular to a fire hazard identification method and system based on image enhancement. The method comprises the following steps: synchronously collecting thermal images through an infrared thermal imager array arranged on the top of the inner side wall of the silo, forming a panoramic thermal image sequence through registration splicing and performing enhancement processing, and extracting a candidate thermal spot region; obtaining the spatio-temporal dynamic evolution characteristics of the thermal spot region through cross-frame tracking, and obtaining a comprehensive confidence score by weighted fusion of the spatio-temporal dynamic evolution characteristics and spatial morphological characteristics; and finally, combining a smoldering physical diffusion model verification to determine the smoldering hazard. The present application realizes early and accurate identification of smoldering hazards in the silo by fusing the dynamic evolution characteristics of the thermal spot region and the physical model verification, effectively overcoming the problems of high false alarm rate and early warning lag of the traditional static temperature threshold monitoring method.
Owner:CHENGAN SHENGBANG BEIJING NETWORK TECH
Manipulator multi-mode tactile perception and object recognition system and method
PendingCN121973235AReduce hardware complexityReduce control complexityProgramme-controlled manipulatorSensor arrayRobot hand
The invention relates to a manipulator multi-mode tactile perception and object recognition system and method, and the system comprises a manipulator actuator, a multi-channel flexible tactile sensor array, a signal collection module, and a processing terminal. Wherein a flexible tactile sensor in the multi-channel flexible tactile sensor array comprises a packaging layer, an electrode layer, a conductive sensitive layer and an elastomer layer, and the multi-channel flexible tactile sensor array is in contact with a target object; a microstructure array is arranged on one side, facing the conductive sensitive layer, of the packaging layer and / or the elastomer layer, and the microstructure array and the conductive sensitive layer form an interlocking / embedding interface. Compared with the prior art, the method has the advantages that the recognition robustness under the complex surface condition is improved, the weight prediction error is reduced and the like.
Owner:SHANGHAI UNIV OF ENG SCI
Underground unmanned vehicle control method and system fusing pushing mode and gesture recognition, and unmanned vehicle
PendingCN122219417AAchieve autonomous switchinglighten the control burdenVehicle position/course/altitude controlPosition/direction control
The application discloses a kind of fusion pushing mode and gesture recognition's underground unmanned vehicle control method, system and unmanned vehicle, comprising: with the tracking result of unmanned vehicle to guide personnel and gesture recognition result as input, the cycle control decision of unmanned vehicle working mode is carried out in combination with environmental perception information, comprising: in response to single control period, guide personnel station position and instruction intention are identified based on tracking result, gesture recognition result and environmental perception information;According to guide personnel station position and instruction intention, the working mode of unmanned vehicle is decided;In response to the working mode decided, the environment passability check result is calculated and the chassis control instruction of unmanned vehicle is output, and the working mode, direction intention, executability state and safety keeping instruction are synchronously controlled unmanned vehicle and visualized display is shown outside;The application can be based on guide personnel continuous tracking combined with the core control scheme of gesture recognition, realize the autonomous switching of unmanned vehicle between following, pushing, parking and other working modes.
Owner:YULIN SAIYI INTELLIGENT TECHNOLOGY CO LTD
An automatic driving forward collision warning method based on capsule network fusion perception
ActiveCN120913177BImprove context-related capabilitiesImprove robustnessBiological modelsScene recognitionNetwork ConvergenceSimulation
The application discloses an automatic driving forward collision warning method based on capsule network fusion perception, and relates to the technical field of collision warning. The application encodes the spatial region with structure and semantic meaning in the original perception image through a semantic capsule structure, and embeds the spatial region into a perception capsule structure, so that multi-level and structured perception enhancement is realized, and the context correlation capability of target identification is effectively improved; with the help of dynamic screening of redundant target capsules corresponding to high-interference semantic items, the probability of misidentification and false alarm of the warning is significantly reduced, and the robustness of the system to interference information in a complex traffic scene is improved; meanwhile, through receiving and buffering the motion intention capsules broadcast by the front vehicle, a cross-vehicle trajectory relay mechanism is constructed, the limitation of traditional single perception based on the vehicle is broken, and multi-vehicle cooperative perception and joint judgment are realized.
Owner:NANJING SHUOXIN TECHNOLOGY CO LTD
N-boc-l-phenylalanine molecularly imprinted polymer, its preparation method and application
PendingCN122103452AUniform particle size distributionImprove adsorption capacityCarbamic acid derivatives preparationOrganic compound preparationPolymer scienceFunctional monomer
The application discloses an N-Boc-L-phenylalanine molecular imprinting polymer and a preparation method and application thereof. The N-Boc-L-phenylalanine molecular imprinting polymer is prepared by using a bulk polymerization method, taking N-Boc-L-phenylalanine as a template molecule and allylamine as a functional monomer, and under the participation of a crosslinking agent and an initiator. The molecular imprinting polymer has specific recognition ability to N-Boc-L-phenylalanine. The maximum adsorption capacity of the molecular imprinting polymer to N-Boc-L-phenylalanine reaches 14.50 mg / g, and the imprinting factor IF value is as high as 10.33. The adsorption amount of the molecular imprinting polymer to N-Boc-L-phenylalanine is significantly higher than that to N-Boc-D-phenylalanine, and the molecular imprinting polymer has good chiral recognition ability. The molecular imprinting polymer can be used for selective recognition, adsorption and enrichment of N-Boc-L-phenylalanine.
Owner:GUANGDONG UNIV OF TECH
A method for intelligent access control and risk warning of hazardous chemical vehicles
PendingCN122573162AAverage emergency response time reducedReduced ability to recognize
This invention discloses an intelligent entry control and risk warning method for hazardous chemical vehicles, belonging to the field of hazardous chemical transportation safety management technology. The method includes: acquiring multi-source data of vehicles to be entered, including carrier qualification data, vehicle equipment status data, cargo risk data, driver status data, and real-time environmental data; normalizing the data of each dimension to calculate an initial risk score; adaptively adjusting the weight allocation of each level based on dynamic environmental factors; calculating the overall risk value through a weighted comprehensive risk scoring function; comparing the overall risk value with multi-level warning thresholds to generate corresponding control instructions; and generating a comprehensive risk impact factor and forming a closed-loop linkage with on-site scheduling. This invention solves the technical problems of incomplete, static, and disconnected entry risk assessment from subsequent operation and management in existing technologies, achieving comprehensive quantitative assessment, adaptive dynamic adjustment, and closed-loop control of hazardous chemical vehicle entry risks throughout the entire process.
Owner:HUIZHOU HARBOR REAL ESTATE INVESTMENT CO LTD
A screw machine positioning mechanism
The present application relates to the technical field of screw installation, and discloses a screw machine positioning mechanism, which comprises a rack, a mounting plate two, a motion execution system, a vision system and a moving speed regulation system. The motion execution system drives the mounting plate two to translate along the XYZ axis; the vision system collects positioning images; the moving speed regulation system comprises a mechanical dynamic performance evaluation module, a motion path evaluation module, a vision system confidence evaluation module, a negative pressure state evaluation module and a moving speed regulation module. Through the collaborative work of multiple modules, the mechanical performance coefficient, the motion path coefficient, the vision confidence and the negative pressure matching coefficient are output based on the parameters of vibration acceleration, tracking error, load, path curvature, moving distance, image definition, illumination intensity, real-time negative pressure value and vacuum establishment time, and finally the moving speed is dynamically adjusted in real time through the speed regulation model. The present application realizes the intelligent balance of positioning accuracy and efficiency under high-speed operation.
Owner:SHENZHEN ASIA TECH CO LTD
Speech recognition and sensitive word detection method
PendingCN121999781Astable retentionReduced ability to recognizeSpeech recognitionPhonetic environmentFeature extraction
The invention relates to a speech recognition and sensitive word detection method. The method comprises the following steps: collecting a speech signal, and carrying out preprocessing and acoustic feature extraction; constructing a speech recognition model, and generating corresponding text data based on the acoustic features; constructing a sensitive lexicon and constructing the sensitive lexicon into a finite automaton state diagram; traversing the text data, and detecting sensitive words according to the determined finite automaton state diagram; according to the method, in a voice environment containing noise, accent or homophone interference, the recognition accuracy of key terms in the field is effectively maintained, keyword recognition leakage and homophone replacement errors are reduced, and the subsequent detection reliability is improved from the source; and meanwhile, through a deterministic matching mechanism of the finite state automaton, the calculation overhead can be reduced, the matching jitter can be reduced, and a more stable hit position and a more stable context fragment can be output.
Owner:STATE GRID FUJIAN ELECTRIC POWER CO LTD +1