Patents
Literature
19results about How to "Incomplete solution" 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
State estimation method, device and equipment for power battery of sweeper
ActiveCN119619869Aresolve accuracyincomplete solutionElectrical testingDesign optimisation/simulationPower batteryBattery charge
The invention relates to a method, a device and equipment for estimating the state of a power battery of a sweeper. The method comprises the following steps: performing impedance characteristic acquisition on a power battery of the sweeper under various working conditions, and performing random low-frequency modulation multi-sine excitation signal measurement to obtain battery working condition characteristic data; performing fitting operation through the equivalent circuit model to obtain a battery health factor model; performing charging process feature extraction analysis to obtain a battery charging curve reconstruction model; carrying out extended Kalman filtering operation to obtain a battery state-of-charge value; performing segment processing and Gaussian process regression calculation on voltage and current data in the charging process to obtain a battery health state value; and updating the polynomial mapping coefficient of the battery health factor model and the weight parameter of the battery charging curve reconstruction model to obtain a target health factor model and a target charging curve reconstruction model. According to the invention, the adaptability and accuracy of the state estimation method in the whole life cycle of the battery are ensured.
Owner:SHENZHEN GRENERGY TECHNOLOGY CO LTD
Display device and sound synthesis method
PendingCN119559922Aimprove continuityimprove integrityMetadata audio data retrievalTelevision system detailsSynthesis methodsAcquisition time
The invention provides a display device and a sound synthesis method, and the method comprises the steps: receiving sound data collected by a sound collector in response to an access instruction of the sound collector, and storing the sound data and corresponding collection time at a preset position; according to an input playing instruction, accompaniment audio data and original sound audio data of a target song are decoded, a start time identifier contained in the accompaniment audio data is detected, and after the start time identifier is detected, sound data are periodically read according to time corresponding to the start time identifier and collection time; when the sound data is read, generating target audio data according to the accompaniment audio data and the read sound data; and when the sound data is not read, generating target audio data according to the accompaniment audio data and the replacement audio data. According to the method, the missing sound data of the user can be filled in a mode of replacing the audio data, the integrity of the target audio is ensured, and the problem that the audio is incomplete in the audio recording process is solved.
Owner:JUHAOKAN TECH CO LTD
Picture classification method based on improved Mama
The invention discloses a picture classification method based on improved Mama. The method comprises the following steps: acquiring an input image to be classified; generating a feature block matrix; extracting and obtaining four down-sampling bidirectional feature maps with different scales layer by layer; gradually restoring the image resolution to obtain two-way feature maps corresponding to four different scales after up-sampling; gradually restoring a high-resolution feature map with the same resolution as the input image; the multi-layer sensing module performs feature mapping on the high-resolution feature map according to the category feature block to generate probability distribution of each category; according to the probability distribution of each category, classifying the input image to be classified, and outputting an image classification result; according to the method, bidirectional feature maps of different scales are extracted layer by layer through progressive down-sampling operation of an encoder, so that global context information of the image is reserved, local detail features are effectively extracted, and the integrity and expression ability of multi-scale features are ensured.
Owner:HEFEI INST OF TECH INNOVATION ENG CHINESE ACAD OF SCI
A textile machine for producing air-purifying fabrics
This invention discloses a textile machine for producing air-purifying fabrics, relating to the field of air-purifying fabric technology. It includes an air-purifying fabric textile machine, a processing platform, an extension processing arm, a rotating shaft, and a heating and shaping cylinder. The processing platform is located on the left side of the front of the air-purifying fabric textile machine, and the extension processing arm is located at the top of the front of the processing platform. A rotating shaft is located on the inner outer surface of one end of the extension processing arm. This invention utilizes a supporting hollow column to increase the support inside the outer sliding wheel, a conductive wire to guide power to the interior of the heating wire, and a gourd-shaped flexible rod to align with the surface of the needle. The heating wire then irons and shapes the fibers on the outer surface, achieving the characteristic of ironing the fibers and reducing fiber retraction. This solves the problem of fibers retraction during loosening, resulting in incomplete loosening, and achieves the effect of ironing the fibers and reducing fiber retraction.
Owner:张红侠
Regulation retrieval method based on knowledge graph multi-hop reasoning query, medium and equipment
PendingCN121996780Aimprove accuracyImprove efficiencySemantic analysisInference methodsTheoretical computer scienceKnowledge graph
The invention discloses a law and regulation retrieval method based on knowledge graph multi-hop reasoning query, a medium and equipment. The method comprises the following steps: firstly, constructing a finance and tax knowledge graph and a vector database; after a query request is received, tax labels and tax concepts are extracted, and a first candidate fragment set is obtained through vector retrieval. And performing one-hop query on the candidate fragment sets in the knowledge graph to obtain associated tax concept nodes and filter the associated tax concept nodes to form an extended tax concept set. Performing one-hop query by taking the extended tax concept set as a starting point to obtain more associated regulation fragments to form a second candidate fragment set; and finally, combining the two candidate fragment sets, and carrying out sorting and screening according to the law and regulation effectiveness, the release time and the semantic similarity to generate a structured final retrieval result. According to the method, through two-time directional query and intermediate concept filtering, the problems of incomplete laws and regulations recall and irrelevant information interference in a multi-hop reasoning scene are effectively solved.
Owner:FUJIAN BOSS SOFTWARE
An information determination method, apparatus, device, and computer readable storage medium
ActiveCN116821900Bimprove accuracyThe test result is accurateBiological modelsPlatform integrity maintainanceDatasheetFeature extraction
Embodiments of the present application disclose an information determination method, which comprises: obtaining a plurality of sample data of a sample abnormal program, wherein the sample data represents corresponding running data of the sample abnormal program at different times during a running process of the sample abnormal program; performing model training on an initial real-time feature extraction model and an initial space feature extraction model based on the sample data to obtain a target real-time feature extraction model and a target space feature extraction model; obtaining a target classification model based on the target real-time feature extraction model and the target space feature extraction model; processing target running data of a to-be-detected program by using the target classification model and a target classifier to determine whether the to-be-detected program is abnormal; and solving the problem of incomplete feature information extracted in related technologies, thereby improving the accuracy of determining an abnormal program. Embodiments of the present application also disclose an information determination device, equipment and a computer readable storage medium.
Owner:CHINA MOBILE (SUZHOU) SOFTWARE TECH CO LTD +1
Passive radar networked signal cooperative complementary sorting method and system
ActiveCN117289213Bincomplete solutioneasy to sortWave based measurement systemsTelecommunicationsPassive radar
The application discloses a passive radar network signal cooperative complementary sorting method and system, wherein the method comprises the following steps: cooperatively complementing mixed alias radiation source pulse sequence signals received by multiple passive radar stations to obtain complemented pulse sequence signals; and sorting the complemented pulse sequence signals by using a cumulative difference histogram method to separate pulse sequences of different radiation sources. Compared with an existing single-station passive radar signal sorting method, the method solves the problem of incomplete pulse sequences caused by pulse loss, greatly improves the correctness of signal sorting, and has better sorting performance, especially when pulse loss is serious.
Owner:XIDIAN UNIV
Peel breaking and kernel removing structure for fruit with complete kernel
PendingCN119453505Aincomplete solutionImprove processing efficiencyFruit stoningStructural engineeringDrive motor
Owner:YICHANG HAITONG FOOD
An automatic film replacing device for automobile front bumper
ActiveCN116985394BIncomplete solutionSolve the troublesome problem of film replacementMechanical engineering
The application relates to the technical field of automatic film replacing, and discloses an automatic film replacing device for a front bumper of an automobile, which comprises a workbench, a fixing frame arranged on the workbench and used for fixing the front bumper, and a film replacing assembly which is movable relative to the front bumper; the film replacing assembly comprises a rotating conversion cylinder, a hot film taking assembly, a hot treatment and mark cleaning assembly, an extrusion drying assembly and an extrusion film applying assembly which are arranged around the rotating conversion cylinder and used for film treatment; the hot film taking assembly, the hot treatment and mark cleaning assembly, the extrusion drying assembly and the extrusion film applying assembly can rotate with the rotating conversion cylinder; the workbench is further provided with an alignment assembly which is used for aligning the hot film taking assembly and the hot treatment and mark cleaning assembly with the front bumper; and the device solves the problems that the traditional automobile film pasting method cannot completely paste the film on the front bumper of the automobile and the film replacing is troublesome.
Owner:CHONGQING GUANGNENG RONGNENG AUTOMOTIVE TRIM CO LTD
Storage method, device, equipment and storage medium for three-dimensional building data
ActiveCN114564542BIntegrity guaranteedincomplete solutionDatabase updatingRelational databasesData transportThree dimensional architecture
The present invention relates to the field of data storage, and discloses a storage method, device, equipment and storage medium for three-dimensional building data. The method comprises: obtaining three-dimensional building data to be stored; analyzing and encapsulating the three-dimensional building data according to a preset analysis algorithm to obtain the overall building data, building component data and mapping relationship data of the three-dimensional building data, wherein the mapping relationship data comprises: mapping relationship data between the building component data and the overall building data; storing the building component data in a mongoDB database, storing the overall building data and the mapping relationship data in a MYSQL database; transmitting the mapping relationship data to an external port for retrieving the stored three-dimensional building data.
Owner:SHENZHEN BIMEI TECH CO LTD
A deposition device and an atomic layer deposition apparatus
A deposition device includes a supply unit with a hollow shell as a reaction chamber and connected to the reaction chamber, wherein the supply unit includes a reactant transmission module, and the reactant transmission module is detachably connected to the reaction unit. An atomic layer deposition device includes a frame and the above-mentioned deposition device, which can be used to prepare a powder surface coating layer. The present invention can effectively solve the problem of cross contamination when depositing different thin film materials and incomplete ALD deposition particle coating layer.
Owner:SHENZHEN YUANSU OPTOELECTRONICS TECH CO LTD
Toughening furnace air grid tuyere cleaning tool
ActiveCN222175057UGuaranteed operating efficiencyGuaranteed production efficiencyCleaning using toolsCleaning using liquidsEnvironmental engineeringMechanical engineering
The utility model discloses a toughening furnace air grid tuyere cleaning tool which comprises a nozzle, the side portion of the nozzle is connected with a handle, the handle is internally provided with a water inlet pipe and an air inlet pipe, the water inlet pipe and the air inlet pipe are both communicated with the nozzle, one end of the water inlet pipe is connected with a water source, and one end of the air inlet pipe is connected with compressed air. The bottom of the nozzle is connected with a scraper blade, the inner side of the scraper blade is contacted with the air grid, and the cleaning tool for the air grid and the nozzle of the toughening furnace is simple and convenient to operate and efficient in cleaning.
Owner:XINYI PHOTOVOLTAIC IND (ANHUI) HLDG CO LTD
Multi-fidelity discrete aerodynamic force modeling method for high-fidelity low-density sampling
PendingCN119294276Aincomplete solutionImprove forecast accuracySustainable transportationDesign optimisation/simulationData informationModelSim
The invention discloses a multi-fidelity discrete aerodynamic modeling method for high-fidelity low-density sampling, and belongs to the field of multi-fidelity aerodynamic modeling. The method comprises the following steps: acquiring a small amount of wind tunnel test data as high-fidelity data; carrying out simulation calculation through XFoil software to obtain a large amount of low-fidelity data; the gradient of the high-fidelity data and the gradient of the low-fidelity data are calculated through the combination of spline interpolation and finite difference; a gradient enhanced Cokriging model is constructed through a small amount of high-fidelity data, a large amount of low-fidelity data and gradients calculated by the high-fidelity data and the low-fidelity data respectively. According to the invention, under the condition of low-density sampling of the high-fidelity data, the problem of low modeling precision caused by missing of the high-fidelity data information is solved by fusing additional gradient information.
Owner:SOUTHWEAT UNIV OF SCI & TECH
Hyperbranched polyamide functionalized graphene oxide modified bismaleimide resin
The invention provides hyperbranched polyamide-functionalized graphene oxide (HPA-GO) modified bismaleimide (BMI) resin, and relates to the technical field of bismaleimide resin.The HPA-GO modified BMI resin is prepared from DMF (N, N-dimethylformamide) dispersion liquid of HPA-GO, diphenyl bismaleimide, deionized water and diallyl bisphenol A. The preparation method comprises the steps that the BMI resin is prepared from the following raw materials, the preparation method comprises the following steps: reacting diphenyl bismaleimide with DMF dispersion liquid of HPA-GO, washing, carrying out suction filtration, drying, adding diallyl bisphenol A, reacting, and carrying out stepped curing to obtain the HPA-GO modified BMI resin.
Owner:BEIHANG UNIV
Classroom facial expression recognition method based on improved RT-DETR model
PendingCN121963268AImprove stabilityimprove accuracyInternal combustion piston enginesBiological modelsPattern recognitionData set
The invention discloses a classroom facial expression recognition method based on an improved RT-DETR model. The method comprises the following steps: 1, obtaining a data set of classroom facial expression images; 2, preprocessing the data set by using a computer; 3, training a data set by using a classroom facial expression recognition detection model based on an improved RT-DETR model; 4, training the classroom facial expression recognition detection model to obtain an optimal detection model; and 5, performing real-time identification detection on the classroom facial expressions of the students in combination with monitoring and an optimal detection model. According to the invention, the CAFI module is designed in the backbone network, so that the classroom facial expression features can be extracted and screened more accurately; an MCFEEConv convolution feature enhancement module is designed in the head network, and the feature expression ability of faces with different distances and different sizes is improved; a RepC3LWGA module is designed in a head network, and joint modeling of local convolution features and global context features is achieved.
Owner:CHANGCHUN NORMAL UNIV
Small-view-field-angle cross-view-angle image geographic positioning method and system
PendingCN119418217Aimprove understandingeasy to handleInternal combustion piston enginesScene recognitionGeolocationSatellite image
The invention provides a small-field-angle cross-view-angle image geographic positioning method and system, and the method comprises the steps: carrying out the feature extraction and weighting processing of a small-field-angle training set obtained through preprocessing through employing a pre-trained OfficientNet network and a triple attention network, and obtaining a ground image feature descriptor set and a satellite image feature descriptor set; calculating the loss by adopting a comparison loss function or a loss function based on a multi-difficulty negative sample weighting strategy, and performing iterative training on the pre-trained OfficientNet network and the triple attention network according to a loss minimization target; and positioning a ground image to be positioned by adopting the trained OfficientNet network and the triple attention network. According to the method, the positioning precision of the to-be-positioned ground image is high, and the recall rates of the trained OfficientNet network and the triple attention network are averagely improved by 10% to 20%.
Owner:Chinese People's Liberation Army Cyberspace Force Information Engineering University
Video processing method, device, electronic device and computer readable storage medium
ActiveCN113343827BImprove experienceincomplete solutionCharacter and pattern recognitionSpeech recognition
The present disclosure relates to a video processing method, device, electronic device and computer-readable storage medium, wherein the method comprises: obtaining a video to be published in a video interactive application; when the video includes news material, obtaining the element content of the news corresponding to the news material, and adding the element content to the video. Through the present disclosure, the problem of incomplete video content caused by processing the video to be published in the related art is solved, thereby achieving the effect of effectively improving the integrity of the video content.
Owner:BEIJING DAJIA INTERNET INFORMATION TECH CO LTD
Travel chain data completion method based on improved rbf neural network model
PendingCN122245090Aimprove integrityincomplete solutionDetection of traffic movementBiological models
This invention relates to a method for completing travel chain data based on an improved Radial Basis Function (RBF) neural network model, belonging to the field of intelligent transportation technology. The method includes: acquiring a user's current travel chain data, wherein the current travel chain data includes at least one travel segment and at least one missing travel segment, the travel segment including public transportation data, and the missing travel segment including walking or cycling data; inputting the user's current travel chain data into a pre-trained improved RBF neural network model to obtain complete travel chain data, wherein the pre-trained improved RBF neural network model is trained based on historical travel chain data, including historical mobile phone signaling data and historical public transportation card swipe data. Through multi-source data fusion and an improved radial basis function (RBF) neural network model, walking or cycling data in the travel chain is automatically identified and completed.
Owner:BEIJING UNIV OF CHEM TECH +1
Platform construction method based on renewable energy agent and system optimization network
PendingCN121903207AIncomplete solutionSolve unsystematic defectsData processing applicationsArtificial lifeData acquisitionSystem optimization
The invention provides a platform construction method based on a renewable energy agent and a system optimization network, and belongs to the technical field of renewable energy technologies and artificial intelligence. The method comprises the following steps: constructing an agent model covering multiple types of renewable energy such as wind power, photovoltaic power and hydropower, integrating multi-source energy data by using a knowledge graph, and constructing a system optimization network; and dynamic regulation and control of the system-level optimization network are realized in combination with deep reinforcement learning. The platform comprises a multi-source energy data acquisition and fusion module, a renewable energy agent modeling module, a system optimization network construction module, a multi-energy collaborative decision module and a dynamic evaluation feedback module. According to the method, the problems of insufficient multi-energy complementarity mining, low dynamic optimization precision, poor decision collaboration and the like in the existing renewable energy system are solved, and the comprehensive utilization efficiency and the regulation and control intelligence level of the renewable energy system are remarkably improved.
Owner:TSINGHUA UNIVERSITY