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

392results about How to "Fine granularity" patented technology

Long text user opinion understanding method and system based on memory enhancement

The invention provides a long text user opinion understanding method and system based on memory enhancement, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining a long text user opinion to be understood, and carrying out the preprocessing of the long text user opinion; mapping the text representation into a low-dimensional dense vector by utilizing a word vector model, taking the low-dimensional dense vector as the input of a memory enhanced neural network model, and generating a structured opinion abstract and a keyword; and post-processing the opinion abstract and the keyword output by the memory enhanced neural network model to obtain normalized structured opinion information, generating an opinion understanding report, and automatically generating a response in combination with a domain dialogue knowledge base and a user portrait.
Owner:广东省众创科技实业有限公司

Synchronous red mud dealkalization method for soil

PendingCN119138299AEnhanced ionization strengthFine granularityGrowth substratesCulture mediaSoil treatmentEdaphic
The invention relates to an aluminum oxide industrial waste residue treatment technology, in particular to a red mud synchronous dealkalization soil treatment method. According to the method, citric acid and calcium nitrate are adopted as treating agents to cooperatively treat the red mud, the sodium content requirement of planting soil is taken as the standard, the red mud is dealkalized to reduce the sodium content, meanwhile, the granularity of the dealkalized red mud is improved, the organic matter content of the dealkalized red mud is increased, and then the dealkalized red mud and normal soil are mixed in proportion to form the dealkalized red mud soil. The physicochemical indexes of the dealkalized red mud soil are as follows: the volume weight is 1.18-1.26 g / cm < 3 >, the organic matter content is 10.6-12.3%, the pH value is 7.2-7.35, the EC is 0.492-0.562 ms / cm, and the specific surface area is 51.49-59.80 m < 2 > / g. The dealkalized red mud soil obtained through the synergistic treatment of the citric acid and the calcium nitrate completely meets the physicochemical properties of the soil and the planting requirements of plants.
Owner:JIANGXI UNIV OF SCI & TECH

Virtual teaching scene description generation method and device, equipment and storage medium

The invention discloses a virtual teaching scene description generation method, device and equipment and a storage medium, and relates to the technical field of knowledge maps, and the method comprises the following steps: respectively obtaining comparison cross parameters of corresponding modes of a time sequence vector, a text vector, a picture vector and an audio vector, and constructing a cross attention matrix based on a plurality of comparison cross parameters; normalizing the plurality of modal vectors through a cross attention matrix to obtain a plurality of normalized modal vectors; iterating a cross attention matrix construction process and a normalization process on the plurality of normalized modal vectors to obtain a plurality of optimal modal vectors, and fusing and mapping the optimal modal vectors to obtain a multi-modal feature vector; the multi-modal feature information is decoded, virtual teaching scene description is generated, and the virtual teaching scene description comprises text information and picture information. According to the invention, deep and accurate fusion of subject knowledge information and teaching events is realized, and finally, high-quality, fine-grained, reasonable and complete virtual teaching scene description is generated.
Owner:ZHEJIANG NORMAL UNIV

Method for preparing ceramic bond through solution heat preservation and superhard grinding tool

The invention provides a method for preparing a ceramic bond through solution heat preservation and a superhard grinding tool. The ceramic bonding agent prepared through a solution heat preservation method is fine in powder granularity and low in sintering temperature and contains a certain amount of crystals, the bonding agent has high impact resistance and self-sharpening performance due to existence of the crystals, and the prepared superhard ceramic grinding tool has the performance of high strength and good sharpness. The method has the advantages of short binding agent preparation period, low equipment investment cost, simplicity in operation and the like. The preparation method of the ceramic bond provided by the invention is not reported.
Owner:江苏赛扬精工科技有限责任公司

Intelligent guarding system for large-scale micro-nano processing laboratory equipment

The invention provides an intelligent guard system for large-scale micro-nano processing laboratory equipment, and the system comprises a data collection module, a risk early warning module, a fault positioning module and an operation and maintenance management module, the fault is traced by using the collected real-time environment data, real-time state data, experimental data, real-time behavior data and identity information, so that the details of the fault can be known in time, and fault maintenance, responsibility investigation and the like can be carried out; the operation and maintenance management module can carry out multi-dimensional operation and maintenance management on the laboratory according to the collected real-time environment data, real-time state data, experimental data, real-time behavior data and identity information, so that the efficiency, the performance and the service life of equipment are improved, the maintenance cost of the equipment is reduced, and effective utilization of social resources is facilitated.
Owner:HONG KONG UNIV OF SCI & TECH (GUANGZHOU)

Multi-agent and multi-mode alignment interaction method and system for review scene

PendingCN121765473ASolve the problem of inability to reach consensus when inconsistent inputSolve the problem of inability to reach consensusBiological modelsInference methodsAlgorithmTheoretical computer science
The invention relates to the technical field of multi-agent systems, and discloses a multi-agent and multi-mode alignment interaction method and system for a review scene, and the method comprises the steps: mapping real-time multi-mode data into a local belief vector through a heterogeneous agent cluster, and calculating the spatial divergence to determine a global cognitive entropy; interaction time sequence gating logic based on entropy flow differential is established, and active alignment is triggered when the global cognitive entropy is larger than a convergence threshold value and a first-order derivative is smaller than a damping threshold value; according to the method, through entropy flow differential control and an active semantic disturbance closed loop, decision oscillation of the multi-agent system in the non-cooperative environment is eliminated, and the reliability of the multi-agent system in the non-cooperative environment is improved. Mathematical convergence of the belief state in an adversarial disguise scene is realized, and the system identification precision in a complex interactive game is improved.
Owner:SHANGHAI SECOND POLYTECHNIC UNIVERSITY +1

Novel double-circular-seam atomizer and atomizing device

PendingCN119304195Ahigh rated pressureImprove crushing effectJet flowMetal powder
The invention belongs to the technical field of powder metallurgy, and discloses a novel double-circular-seam atomizer and an atomizing device.The novel double-circular-seam atomizer comprises an atomizer base body, a vertically-through melt channel is formed in the middle of the atomizer base body and used for allowing a flow guide nozzle to penetrate through, and the atomizer base body is provided with a cavity coaxial with the melt channel and a circular-seam spraying hole; the cavity is used for inputting high-pressure gas, and the circular seam spraying hole communicates with the cavity and is used for spraying out the high-pressure gas to form high-speed gas flow so as to break metal melt liquid flow flowing out of the flow guide nozzle. The number of the circular seam spraying holes is two, the two circular seam spraying holes are the first circular seam spraying hole and the second circular seam spraying hole, the second circular seam spraying hole surrounds the first circular seam spraying hole from the outer side of the first circular seam spraying hole, and on any longitudinal section plane of the atomizer base body, the jet flow center lines of the second circular seam spraying hole and the first circular seam spraying hole intersect at one point; the melt liquid flow crushing effect can be improved, the diffusion angle of metal liquid drops is increased, formation of large particles is reduced, and metal powder with smaller particle size and better sphericity degree is obtained.
Owner:CHONGQING WANGBIAN ELECTRIC GRP CORP

Optimization method for brain glioma prognosis prediction model

InactiveCN119092106ASolve representation problemsgreat innovation valueMedical data miningHealth-index calculationMedicineKnowledge graph
The invention discloses an optimization method for a brain glioma prognosis prediction model. The optimization method comprises the following steps: S1, constructing a prior knowledge graph for brain glioma prognosis prediction; s2, establishing a brain glioma prognosis prediction model based on a priori knowledge graph; s3, carrying out interpretability research in the brain glioma prognosis prediction model; and S4, constructing a mixed enhanced intelligent prototype verification system for brain glioma prognosis prediction. According to the method, multi-mode and multi-level medical priori knowledge used by professional doctors in the disease diagnosis process is introduced, feature extraction is carried out on the multi-mode and multi-level medical priori knowledge through the knowledge graph, deep learning and other technologies, the priori knowledge graph oriented to brain glioma prognosis prediction is constructed, the characterization problem of the medical priori knowledge is solved, and the accuracy of brain glioma prognosis prediction is improved. The method provides theoretical basis and data support for subsequent auxiliary diagnosis decision making, and has great innovation value.
Owner:JIANGSU CANCER HOSPITAL

Unmanned aerial vehicle insulator inspection system based on multi-light fusion and method thereof

The invention belongs to the technical field of unmanned aerial vehicle inspection, and particularly relates to an unmanned aerial vehicle insulator inspection system and method based on multi-light fusion. Comprising an unmanned aerial vehicle platform and a ground control station. The unmanned aerial vehicle platform is used for carrying inspection equipment and inspecting the insulator according to a preset path; comprising an unmanned aerial vehicle body, a multi-light fusion sensor module, a data processing module, a control module and a communication module, the multi-light fusion sensor module integrates a visible light sensor, an infrared sensor and an ultraviolet sensor and is used for acquiring visible light image information, infrared thermal image information and ultraviolet image information of the insulator, potential faults can be found in the early stage through the three-light fusion technology, and important data support is provided for preventive maintenance; through integration of data of different wavelengths, insulator fault diagnosis under the three-light fusion technology reduces the possibility of misjudgment of insulator faults, and high detection reliability and high efficiency can be maintained under various environmental conditions.
Owner:HAIBEI POWER SUPPLY COMPANY STATE GRID QINGHAI ELECTRIC POWER +1

Large language model enhancement method, device and equipment based on Internet search

The embodiment of the invention provides a big language model enhancement method, device and equipment based on Internet search, and the method comprises the steps: responding to a search request of a user, and obtaining retrieval result data; constructing a first block tree based on the retrieval result data, and performing first pruning operation on the first block tree based on an embedded model to obtain first retrieval refined data; and constructing a second block tree based on the first retrieval refined data, and performing a second pruning operation on the second block tree based on the path generation model to obtain second retrieval refined data, the second retrieval refined data being used for inputting the large language model to generate an answer conforming to the search request. In the embodiment of the invention, the refining speed of the embedded model is relatively high, the refining granularity of the path generation model is finer, and the retrieval result data is refined by combining the embedded model and the path generation model, so that the retrieval refined data with relatively high quality can be obtained, and the answer quality of the large language model is further improved.
Owner:RENMIN UNIVERSITY OF CHINA +1

Low-complexity digital pre-equalizer based on frequency domain comb pilot channel estimation

The invention belongs to the technical field of optical communication, and particularly relates to a low-complexity digital pre-equalizer based on frequency domain comb pilot channel estimation. The device comprises a data sending module, a channel response test module and a digital signal pre-equalization module, the data sending module comprises an initial comb signal generation part and a frequency component phase rotation part; the channel response test module comprises a signal frequency difference estimation and recovery part and a channel amplitude-frequency and phase-frequency response test part; the digital signal pre-equalization module comprises a filtering coefficient generation part and a sending signal convolution pre-equalization part; according to the invention, a frequency domain comb pilot signal is sent to analyze channel amplitude-frequency and phase-frequency response, so that a pre-equalizer for pre-compensating channel response at a sending end is generated; the method has the characteristics of high granularity, high precision, robust transmission signal system and the like, and can be applied to various scenes such as polarization multiplexing long-distance single-carrier coherent optical transmission, mode multiplexing short-distance intensity modulation direct detection systems and the like.
Owner:FUDAN UNIVERSITY

High-frequency high-permeability metal soft magnetic powder core and preparation method thereof

The invention relates to the field of metal soft magnetic materials, in particular to a high-frequency high-permeability metal soft magnetic powder core and a preparation method thereof. The preparation method comprises the following steps: S1, screening magnetically soft alloy powder with a preset particle size; s2, preparing passivation powder; s3, preparing granulation powder; s4, a blank is prepared through compression molding; s5, the blank piece is subjected to curing treatment; and S6, the cured part is subjected to high-temperature heat treatment in vacuum, and the high-frequency and high-permeability metal soft magnetic powder core is obtained. The preparation method disclosed by the invention is simple, mild in reaction condition, low in cost and capable of realizing automatic large-scale production. The high-frequency and high-permeability metal soft magnetic powder core prepared by the invention has high frequency, high magnetic induction intensity and high unit power density, particularly, the internal stress of a metal soft magnetic material is released to the greatest extent by adopting high-temperature heat treatment, the coercive force is reduced, the density and the permeability are remarkably improved, and the high-frequency and high-permeability metal soft magnetic powder core is widely applied to DC-DC and power supply circuits with ultrahigh switching frequency and high magnetic conductivity. And a MHz-level power supply circuit.
Owner:SHENZHEN TOPSUN TECHNOLOGY CO LTD

Synchronous grouting material based on muddy silt shield muck and preparation method thereof

The invention relates to a synchronous grouting material based on muddy silt shield muck and a preparation method thereof, and the synchronous grouting material comprises the following raw materials in parts by weight: 13 to 16 parts of cement, 16 to 20 parts of slag, 142 to 147 parts of fine sand containing silt powder, 0.03 to 0.1 part of trimethylsilyl ethyl acetate, 0.07 to 0.17 part of disodium hydroxyethylphosphonate, 0.03 to 0.1 part of pentasodium amino trimethylene phosphonate and 63 to 67 parts of water. According to the invention, the fine sand containing mud powder is used as a main raw material to replace bentonite and fine sand in synchronous grouting in the prior art, and is combined with a specific cement additive, so that the compressive strength and the impermeability of the synchronous grouting material are effectively improved through the synergistic effect of the components, local materials can be used, and the outward transportation and disposal cost of a large amount of muck can be greatly reduced.
Owner:CHINA CONSTR FIFTH ENG DIV CORP LTD +1

Distribution electric quantity prediction method based on electric quantity big data

The invention relates to an issued electric quantity prediction method based on electric quantity big data, and the method comprises the following steps: S1, obtaining and collecting the power utilization property and network structure data of a load supplied by a transformer area, and carrying out the analysis and control, and improving the quality of line loss basic data in the same period; s2, constructing an electricity sale quantity prediction model, and predicting future electricity sale quantity; s3, establishing a feedback loop, continuously self-calibrating the electricity sale quantity prediction model by using an error correction method, and carrying out future electricity sale quantity prediction correction by incorporating an event, updating and error correction means; s4, according to the corrected future electricity sale quantity, predicting line transformer loss electricity quantity based on a line transformer loss electricity quantity prediction model, and calculating issued electricity quantity based on the predicted line transformer loss electricity quantity and the future electricity sale quantity; and S5, displaying the historical electricity sale quantity, the historical power supply quantity, the predicted future electricity sale quantity and the predicted issued electricity quantity in a chart form. According to the method, complex time dependency and nonlinear fluctuation can be captured, and the accuracy and fine granularity of issued electric quantity prediction are improved.
Owner:STATE GRID INFO TELECOM GREAT POWER SCI & TECH

Urban flood disaster information model construction method and application

The invention belongs to the technical field of disaster data storage, and discloses an urban flood disaster information model construction method and application, and the method comprises the steps: constructing an urban flood disaster information model through employing urban flood disaster data; wherein entities and relationships in the urban flood disaster information model correspond to entities and relationships in the urban flood disaster data; entities in the urban flood disaster data comprise basic entities and attribute entities, and the attribute entities are attribute features of the basic entities; the relationship in the urban flood disaster data comprises a spatial relationship and a semantic relationship between the basic entities. The invention further correspondingly provides related application based on the urban flood disaster information model. According to the method, urban flood disaster information modeling is constructed, and multi-source heterogeneous data is fused in combination with time sequence data and a spatial relationship, so that the comprehensiveness of urban flood disaster knowledge expression can be improved, and multi-element integration and analysis management of urban flood disaster data can be realized.
Owner:HUAZHONG UNIV OF SCI & TECH

Beneficiation method for refractory iron ore with symbiotic hematite, limonite and siderite

The invention discloses a beneficiation method of refractory iron ore with symbiotic hematite, limonite and siderite, which comprises the following steps of: crushing weakly magnetic refractory iron ore to below 100mm in a closed circuit, then sequentially carrying out three times of dry screening to obtain four particle fractions of 0-6mm, 6-15mm, 15-40mm and 40-100mm, pre-selecting the particle fractions of 6-15mm by adopting a dry high-intensity magnetic separator, pre-selecting the particle fractions of 15-40mm by adopting a chunk jigger, pre-selecting the particle fractions of 40-100mm by adopting a photoelectric intelligent separator, and pre-selecting the particle fractions of 40-100mm by adopting a high-intensity magnetic separator; photoelectric intelligent pre-selected concentrate is crushed to 0-40 mm through a fine crushing closed circuit, then jigging pre-selected concentrate is combined, then the photoelectric intelligent pre-selected concentrate is crushed to 0-6 mm through an ultra-fine crushing closed circuit, an ultra-fine crushing product is combined with the 0-6 mm fraction, then wet type strong magnetic pre-selection is conducted through a coarse grain wet type strong magnetic separator, the pre-selected concentrate is subjected to ore grinding-fine grain wet type strong magnetic one-coarse one-scavenging one-coarse one-scavenging one-fine one-scavenging reverse flotation, and the final concentrate is obtained. And final concentrate is obtained. The invention has the advantages of large raw ore selection granularity, large tailing discarding amount, low energy consumption, good separation effect and the like.
Owner:NORTHEASTERN UNIV CHINA +1

Prometheus-based dynamic label setting method and system for monitoring system

The invention relates to the technical field of big data platform monitoring, in particular to a prometheus-based dynamic label setting method and system for a monitoring system, and the method comprises the following steps: in a Prometheus configuration file, carrying out the filtering, renaming and adding operation on a label obtained from a Kubernetes API (Application Program Interface) by utilizing a relatablconfiguration item, so as to achieve the dynamic setting of monitoring labels of service and pod in Kubernetes; writing and executing a shell script through a Shell-Operator tool, monitoring a Kubernetes event, and dynamically setting or modifying a monitoring label for the Pod according to the label and node information of the Pod; the prometheus-based monitoring system dynamic label setting method and system provided by the invention have the beneficial effects that monitoring requirements in different scenes are flexibly adapted, and codes or deployed application programs do not need to be modified; the monitoring requirement of finer granularity can be met; detailed information of a specific scene or event can be retrieved; the requirement of more accurate alarm of specific monitoring data can be met; and rapid positioning and source tracing can be provided for troubleshooting and diagnosis.
Owner:SHANDONG LANGCHAO YUNTOU INFORMATION TECH CO LTD

Airport scene airborne situation enhancement method based on multi-modal information fusion

Relates to the technical field of airborne situation awareness of large-scale airport scene operation, in particular to an airport scene airborne situation enhancement method based on multi-modal information fusion, which comprises the following steps: acquiring an air traffic control instruction text and a sliding track image of an aircraft, and respectively performing feature extraction on the air traffic control instruction text and the sliding track image to obtain a feature extraction result; obtaining text features and visual features; performing multi-modal feature fusion on the text features and the visual features based on an adaptive Transform network to obtain multi-modal features; performing intention recognition and key parameter analysis on the multi-modal features to obtain aircraft behavior intention and aircraft key parameters; taking the behavior intention of the aircraft and the key parameters of the aircraft as airborne situation auxiliary information, and providing assistance for subsequent flight decision making; according to the invention, the understanding capability of the air traffic control instruction can be improved.
Owner:BEIHANG UNIV

Ship abnormal behavior identification method and device

The invention provides a ship abnormal behavior identification method and device, and belongs to the technical field of ship transportation, and the method comprises the steps: extracting a ship track based on AIS data; compressing the ship trajectory, and discretizing ship attributes corresponding to the ship trajectory to obtain ship behavior feature data; based on the ship behavior characteristic data, generating ship behavior characteristic sequence embedding quantity; inputting the ship behavior feature sequence embedding quantity into the trained sequence-to-sequence network model to obtain ship behavior identification information; the network model comprises an encoder and a decoder; and determining an abnormal score of the ship behavior feature sequence embedding amount, and obtaining a ship abnormal behavior identification result based on the abnormal score and the ship behavior identification information. According to the method, the trained sequence-to-sequence network model is adopted, and the abnormal score of the embedding amount of the ship behavior feature sequence is combined, so that the technical problem that the ship abnormal behavior is difficult to accurately and reliably identify in the existing scheme is solved.
Owner:WUHAN UNIV OF TECH

Enterprise knowledge graph reasoning and complementing method and reasoning and complementing system

The invention discloses an enterprise knowledge graph inference completion method and inference completion system, and the method comprises the steps: obtaining a to-be-completed knowledge graph of a target enterprise, inputting the to-be-completed knowledge graph into a trained knowledge graph embedding model, and predicting an incomplete triple to achieve the inference completion of the knowledge graph; wherein the knowledge graph embedding model comprises an entity node coding module, a multilayer graph convolutional neural network module, a Softmax pooling layer and a gating neural network based on a self-attention mechanism. According to the method, the knowledge graph embedding model can provide more accurate semantic information for feature interaction, multi-level feature interaction and aggregation of the triple on sub-tensor kernel granularity and global granularity can be realized, and hidden semantics behind entities and relationships of the knowledge graph can be more efficiently mined. Therefore, the knowledge graph completion accuracy, the semantic modeling capability, the interpretability and the like are obviously improved.
Owner:CHINA TOBACCO ZHEJIANG IND CO LTD

Platinum-carbon catalyst as well as preparation method and application thereof

The invention provides a platinum-carbon catalyst as well as a preparation method and application thereof, and relates to the technical field of catalysts. The platinum-carbon catalyst is prepared from the following raw materials: a carbon carrier, a platinum precursor and ethylene glycol, wherein the ethylene glycol is simultaneously used as a solvent and a reducing agent. The preparation method comprises the following steps: carrying out heat treatment on the carbon carrier; taking a platinum precursor, ethylene glycol and the carbon carrier subjected to heat treatment, mixing, stirring and performing ultrasonic treatment to obtain a mixed material; adjusting the pH value of the mixed material, and then raising the temperature for reaction; and filtering, washing and drying the reactant in sequence to obtain the product catalyst. A reducing agent and a protective agent do not need to be additionally added in the preparation process, so that the production cost is reduced; meanwhile, the technological process is optimized, operation is easy, waste and loss caused by slurry transfer are avoided, and the product catalyst is good in particle uniformity, uniform in dispersion, excellent in performance and capable of being applied to preparation and assembly of fuel cell products.
Owner:CHENGDU DONGFANG KWH ENVIRONMENTAL PROTECTION CATALYSTS

Speech synthesis method and device

The invention provides a voice synthesis method and device, and relates to the technical field of voice processing, and the method comprises the steps: obtaining a target image and a speaking manuscript, inputting the target image and the speaking manuscript into a pre-trained voice synthesis model, and obtaining a target synthesis voice; wherein the target image comprises a plurality of pieces of visual information, the target synthetic speech comprises a plurality of acoustic features, and one piece of visual information corresponds to at least one acoustic feature; the speech synthesis model is obtained by training based on a multi-modal data set, and the multi-modal data set is obtained by performing modal enhancement on a target data set. According to the method provided by the invention, modal enhancement is performed on the existing voice data set to construct the multi-modal data set, so that the problem of scarcity of the data set is solved; according to the one-to-one correspondence between the visual information in the static image and the acoustic features in the voice audio, based on the voice synthesis model obtained through multi-modal data set training, the synthesized target synthesis voice has a finer-grained voice style.
Owner:TSINGHUA UNIVERSITY

Salt leg device and evaporating crystallizer with same

The utility model provides a salt leg device and an evaporating crystallizer with the same, and belongs to the technical field of chemical engineering and environmental protection, the salt leg device comprises a salt leg main body, an elutriation pipeline and a discharge pipeline, an elutriation cavity is arranged in the salt leg main body, and a feed port is arranged at the top of the salt leg main body; the elutriation pipeline is communicated with the salt leg main body and comprises a first branch, a second branch and a third branch which are sequentially arranged along the salt leg main body from top to bottom; the discharging pipeline is arranged at the bottom of the salt leg main body. When the salt leg is used, evaporation mother liquor enters the elutriation cavity through the feeding port, elutriation water enters the salt leg body from the upper portion, the middle portion and the lower portion of the salt leg body through the first branch, the second branch and the third branch, salt discharging slurry generated after elutriation flows out through the discharging pipeline, elutriation is carried out at different positions of the salt leg body, and therefore the better elutriation effect is achieved. The quality of the product salt is improved; according to the salt leg device provided by the utility model, the problem that the salt quality of a product elutriated by a salt leg in the prior art is not high is solved.
Owner:BEIJING JINDAYU ENVIRONMENT TECH CO LTD

Internet of things card package configuration method and system based on data analysis

The invention discloses an Internet of Things card package configuration method and system based on data analysis, and relates to the field of Internet of Things card package management, and the technical scheme is characterized in that the method comprises the steps: collecting comprehensive user information in a period time, carrying out the format conversion of the comprehensive user information, and obtaining standard comprehensive data; using an improved multi-feature K-means technology to analyze the standard comprehensive data of the users, grouping the Internet of Things card users, and obtaining multiple groups of data sets; constructing and using the sample set to train a package personality design model, importing a plurality of groups of real-time data sets into the trained package personality design model, and obtaining a real-time Internet of Things card package scheme; visual interaction is carried out on the internet of things card package scheme, and personalized configuration of the internet of things card package is realized through data analysis.
Owner:SHENZHEN MUSMOON TECH CO LTD

Text sentiment analysis method and system of M-BiLSTM model

PendingCN119129576AAccurate Emotional TendencyComprehensive and accurate syntactic parsing resultsBiological modelsNatural language data processingGraphicsSyntactic ambiguity
The invention belongs to the technical field of natural language processing, and discloses a text sentiment analysis method and system of an M-BiLSTM model based on fusion of multiple syntactic parsers, and the method comprises the steps: carrying out the syntactic analysis of input data through a plurality of external syntactic parsers, and obtaining a plurality of syntactic analysis trees; executing a syntactic parse tree fusion algorithm on the parse tree to obtain a new syntactic parse tree, and constructing a corresponding graph structure to obtain a syntactic enhanced graph; the method comprises the following steps of: preprocessing a text, inputting the preprocessed text into a Bert layer module to obtain a dynamic word vector, capturing an important part of context information of the text through an LSTM (Long Short Term Memory) fused with a Mogrimer structure to obtain a hidden context representation of an input sentence, inputting the hidden context representation and a syntactic enhancement graph into a GCN (Graphics Context Network) to extract an important emotion dependency relationship about a specific aspect, and finally performing emotion classification. According to the method, the problem that a syntactic analysis result is inaccurate when a single syntactic analyzer analyzes a complex long sentence with syntactic ambiguity can be effectively solved, so that the sentiment classification accuracy is improved.
Owner:HUBEI UNIV

Synthesis method of chloride-free cationic rosin size emulsifier

The invention provides a synthesis method of a chloride-free cationic rosin size emulsifier, which comprises the following steps: adding water to dilute dimethyl diallyl ammonium chloride, acrylamide and methacryloyloxyethyl trimethyl ammonium chloride according to a certain proportion to prepare a monomer mixed solution; the monomer mixed solution and the initiator solution are simultaneously pumped into a first microchannel reactor for polymerization reaction, the reaction temperature is 60-100 DEG C, the pressure is 0.2-1.4 Mpa, the retention time is 0.5-3 min, and a cationic polymer is obtained; and simultaneously pumping the cationic polymer and glyoxal into the second microchannel reactor for continuous reaction at the reaction temperature of 10-20 DEG C under the pressure of 2-4.0 Mpa for 0.5-3 minutes. The reaction time is greatly shortened by adopting the microchannel reactor, the method is suitable for industrial production, the synthesized chloride-free cationic rosin size emulsifier is safe, non-toxic, easy to dissolve in water, strong in cohesion, good in hydrolytic stability and free of gelling in 80 days, and rosin emulsion prepared by utilizing the cationic emulsifier is fine in granularity, good in stability and free of chloropropanol.
Owner:SHANGHAI DONGSHENG NEW MATERIALS

Subject cross measurement method based on keywords

The invention relates to the field of interdisciplinary, in particular to a subject interdisciplinary measurement method based on keywords. The measurement method mainly carries out analysis from three dimensions: semantic analysis: processing a corpus in two modes to obtain a matrix and a vector sequence, and carrying out cosine calculation on the matrix and the vector sequence to obtain an index reflecting the similarity of subject knowledge; the hierarchical structure analysis is to analyze and determine subject keyword contribution degree and quantify knowledge distance based on a hierarchical structure, and calculate the subject keyword contribution degree and the knowledge distance to obtain an interdisciplinary measurement index; the network structure analysis comprises the following steps: researching a keyword network to obtain an influence index of a node in the network, applying the index to multiple subjects, and calculating to obtain an interdisciplinary intensity measurement index based on a network structure; and finally, carrying out multi-index synthesis on the three dimensions through an entropy weighting method so as to carry out evaluation on the interdisciplinary interaction strength. According to the method, the problems of insufficient fine granularity and insufficiency in current subject cross detection are solved.
Owner:CHENGDU UNIV OF INFORMATION TECH

In-furnace high-ventilation efficient sintering process

The invention relates to the technical field of sintering, and discloses an in-furnace high-permeability efficient sintering process which comprises the following steps: step 1, selecting raw ore; step 2, proportioning raw ore; 3, high-quality lime application; step 4, steam preheating; step 5, sintering process control; and 6, sintering is completed. In the first step, the proportion of small-particle-size raw ore in the proportion is increased to 20%, the compactness and uniformity of a sintered block are improved, combination is easier during sintering, and therefore the strength and stability of a final product are improved, in the second step, the average particle size is controlled to be 5 mm, the particle size smaller than 1 mm is smaller than 5%, and the particle size larger than 3 mm is larger than 65%. The method ensures good fluidity and effective reaction of the material in the sintering process, the moisture content is controlled to 6.8-8%, pulverization is reduced, the strength and stability of the sintered ore are improved, and the beneficial effects of improving the drum strength and metallurgical performance of the sintered ore and ensuring long-period stable and smooth operation of the blast furnace condition are achieved.
Owner:XUZHOU HUAHONG SPECIAL STEEL CO LTD

Automobile part abnormity monitoring method and system based on AI visual inspection

The invention provides an automobile part abnormity monitoring method and system based on AI visual inspection, and relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring an original part production video of a target automobile part, segmenting the original part production video according to a corresponding production link, and outputting a plurality of segmented part production sub-videos corresponding to the target automobile part; performing video frame optimization on each segmented part production sub-video, and outputting a plurality of optimized part production sub-videos corresponding to the target automobile part; and performing anomaly identification on each optimized part production sub-video by using the updated target neural network, and outputting a plurality of part anomaly data corresponding to the target automobile part. Based on the above content, the reliability of abnormal monitoring of the automobile parts can be improved.
Owner:YATONG AUTOMOBILE PARTS (CHANGSHU) CO LTD

Continuous granulating crusher for molten and semi-molten steel slag

The invention discloses a continuous granulating crusher for molten and semi-molten steel slag, which solves the problem of crushing high-temperature steel slag. The device comprises an equipment rack, a power grinding disc assembly, a power steel roller assembly, a steel slag collecting assembly and a crushing cavity assembly, the power grinding disc assembly is arranged on the lower portion of the equipment rack, and the power steel roller assembly is arranged on the upper portion of the equipment rack and comprises a crushing roller, a bearing assembly, a hydraulic motor and a water medium rotating connector. The crushing roller is internally provided with a water medium cooling channel and is connected with a water cooling system, the crushing roller is mounted on the equipment rack through a bearing, a sliding block and linear sliding fit, and a linear hydraulic jacking cylinder is arranged between the sliding block and the equipment rack; the steel slag collecting assembly is arranged on the equipment rack on the periphery of the grinding disc, and the crushing cavity assembly is arranged on the equipment rack on the periphery of the crushing roller. The steel slag roller crusher is continuous production equipment, crushing at a uniform speed is basically realized, and the granularity of the crushed steel slag is better than that of the traditional steel slag roller crusher.
Owner:SHANDONG SHANKE TONGCHUANG ENVIRONMENTAL ENG DESIGN INST CO LTD +1