340 results about "Gradient boosting decision tree" patented technology

The invention discloses an electric energy metering box fault prediction method and system based on big data analysis, relates to the technical field of smart power grids, and solves the problems of progressive aging missing detection and instantaneous interference misjudgment caused by dependence on single parameter threshold alarm and fault positioning misalignment caused by multi-source data isolated analysis in the prior art. According to the scheme, electrical, environment and equipment state parameters are collected in real time through a multi-dimensional sensing network; the error drift of the mutual inductor is dynamically predicted based on an LSTM-Kalman filtering model, and core breakdown early warning is realized in combination with wavelet transform; outputting a corrected resistance value and a fault mark by using a BP neural network; predicting the life of the piezoresistor by adopting a gradient boosting decision tree and fusing lightning overvoltage characteristics; the transient interference is suppressed through the combination of a Transform self-attention mechanism and dynamic time warping; according to the method, the aging detection precision and the complex environment adaptability are remarkably improved, the misjudgment rate is reduced, and the multi-fault associated positioning and active defense capability is realized.

The invention discloses an industrial personal computer and multi-graphics card collaborative parallel computation acceleration system, which relates to the technical field of industrial resource allocation and parallel computation, and comprises a resource monitoring and predicting module, a resource management module and a prediction type resource preparation module, the task splitting and collaborative execution module comprises a task splitting module, a cross-node collaborative module and a collaborative operation engine; the intelligent scheduling and dynamic resource allocation module comprises an intelligent scheduler, a dynamic resource allocation module and a conflict avoidance module. According to the method, the GPU video memory utilization rate, the core utilization rate, the temperature, the video memory fragment rate, the available video memory total amount, the CPU core total utilization rate, the load condition and the idle core number index are collected in real time through a resource monitoring module, and the video memory capacity, the GPU core occupancy rate and the CPU load requirement are predicted in advance before a task is submitted in combination with a gradient boosting decision tree and a neural network prediction model; and resources are reserved, so that the scheduling delay is remarkably reduced, and the scheduling hit rate is improved.

The invention relates to the technical field of intelligent gardens and precise irrigation, and particularly discloses an intelligent irrigation monitoring method and system. According to the method, a multi-source sensor array is deployed, Kalman filtering is adopted to fuse environmental data, and a three-dimensional state vector input reinforcement learning model is constructed to generate an irrigation decision; predicting a vegetation water demand by combining a gradient lifting decision tree, forming a graded irrigation strategy and converting the graded irrigation strategy into a water pump control instruction; soil humidity feedback data are collected in real time, decision model parameters and filtering rules are dynamically adjusted, and closed-loop optimization is achieved. Through multi-source data fusion and a self-adaptive decision-making mechanism, the irrigation precision and the water resource utilization rate are remarkably improved, meanwhile, the response capacity of the system to the vegetation growth dynamic state and the environment change is enhanced, and the beneficial effects of optimization process closed loop, decision dynamic adaptation and controllable resource consumption are achieved.

A dynamic real estate valuation system based on multiparametric market indicators, which includes the following: a valuation engine configured to generate real-time results for property valuation; a multitude of distributed data ingestion and processing units configured to capture heterogeneous data sources, including historical property transaction data, real-time property listings, zoning and land use records, macroeconomic indicators, geospatial data, environmental sensor outputs, and sentiment-derived metrics; a model orchestration control unit comprising a stack of machine learning models, wherein the models include at least a gradient boosting decision tree model, a long-short-term memory (LSTM) time series forecaster, and an enhancement learning module that iteratively optimizes the model parameters based on the observed evaluation accuracy; a data contextualization controller configured to apply dynamic weighting to each input parameter based on the geographic, temporal, and market context by executing decay functions and location-specific rule matrices; a physical property valuation terminal (PVT) that includes an edge processing unit (EPU), geolocation circuitry, secure communication interfaces and a touch-based user interface; a valuation book subsystem configured to hash the valuation output, timestamp, and signatures of the input record into a blockchain-based distributed ledger; wherein the system is designed to continuously recalibrate its valuation results by comparing the predicted valuations with the actual sales or rental prices, and wherein the physical terminal is designed to produce a legally certifiable valuation document with embedded provenance data.

The invention discloses a power transmission line icing intelligent early warning method, system and device and a medium, and the method comprises the steps: obtaining icing state data and meteorological data, and dynamically adjusting the collection frequency and a dormancy strategy; performing data preprocessing and cleaning on the acquired data; extracting time-frequency features through wavelet packet transformation and a self-attention mechanism, and fusing the spatial dependency relationship and cross-modal interaction information of multiple monitoring points by using a graph neural network to obtain enhanced icing state characterization; performing icing risk prediction by adopting a gradient boosting decision tree model to obtain an icing risk prediction result; and analyzing an icing risk prediction result by using an interpretable tool, identifying a key factor which has the greatest influence on icing risk prediction, dynamically adjusting an early warning level according to the key factor, and generating an early warning and maintenance suggestion. Therefore, the monitoring real-time performance and the early warning timeliness are improved.

The invention relates to the technical field of oil and gas well management, in particular to an intelligent remote transmission control oil and gas well system based on the Internet of Things and multi-dimensional physical sensing feedback. Comprising a multi-dimensional sensor module; a 4G unvarnished transmission communication module and an intelligent remote decision module; the intelligent remote decision-making module is used for analyzing the collected data and generating a control strategy based on a self-adaptive gradient lifting decision-making tree algorithm; and the wide-temperature adaptive power supply module is used for providing continuous power supply for the system based on a multi-energy collaborative energy management algorithm and realizing energy optimization in an off-grid environment. By integrating multi-dimensional physical quantities such as pressure, flow, temperature and vibration, a multi-parameter coupled state space model is constructed, high-confidence real-time data input is provided for control strategy generation, limitation of traditional data processing on dimension coverage and feature extraction is broken through, and comprehensiveness and accuracy of gas well operation state evaluation are improved.

The invention provides a unified authentication and data authority management and control method and system for a big data component. The method comprises the steps of performing validity verification on an identity certificate and generating a unified identity token; obtaining an identity token bound with the data access request through the unified identity token; based on the identity token bound with the data access request, performing permission decision through a preset strategy rule to obtain a permission decision result; obtaining an adjusted permission decision result based on the user attribute, the current operation environment and the access mode; embedding the access traceability representation into the adjusted permission decision result to obtain processed structured data; and obtaining an audit record and a compliance report based on a data access request of the user, the adjusted permission decision result and the processed structured data. Based on the user attributes and the real-time operation environment, the authority decision result is dynamically adjusted by using the gradient boosting decision tree and the attention mechanism, so that cross-component unified management is realized, and the problem of authority strategy stiffness is solved.

The invention relates to the technical field of power equipment state monitoring, and discloses a cable state fault prediction method based on multi-source data fusion. According to the method, a digital twinborn model is constructed by acquiring multi-source data, and a theoretical health baseline changing along with working conditions is simulated and calculated in real time. And comparing the base line with the measured data to generate a thermoelectric coupling matrix with quantitative deviation, and diagnosing the degradation state according to the thermoelectric coupling matrix. And when the deviation exceeds a threshold value, performing attribution analysis by using a gradient boosting decision tree model, and generating a visual spectrogram associated with the partial discharge and the root cause. And finally, the defect type is judged by intelligently identifying a high-risk visual mode on the spectrogram, and the high-risk state is predicted. According to the method, working condition interference is filtered through dynamic reference, causal diagnosis is performed, the problem of high false alarm rate in the prior art is solved, and the prediction accuracy is remarkably improved.

The invention provides an enterprise intelligent finance and taxation system fusing supervised learning and a block chain, and solves the core technical problems of insufficient data credibility, transparent contradiction between privacy protection and supervision, AI model training data island and the like of a traditional finance and taxation system. According to the system, an innovative technical fusion scheme is adopted, bank API, OCR recognition, voice input and other multi-source financial data are integrated through a multi-modal data fusion unit, and high-quality data fusion is achieved through confidence evaluation and an intelligent conflict resolution algorithm; an intelligent classification unit based on BERT deep learning integrates a pre-training model with a business rule engine and a gradient boosting decision tree, and accurate and automatic classification of financial transactions is achieved. A complete technical solution is provided for enterprise finance and taxation digital transformation, intelligent, automatic and credible processing of finance and taxation businesses is achieved on the premise that data safety and privacy protection are guaranteed, and the method has wide market application prospects.

The invention relates to the technical field of power system power distribution network fault detection, in particular to an arc fault diagnosis and analysis method based on an artificial intelligence algorithm, and the method comprises the four steps: synchronous data collection and topological excitation, deployment of terminals at transformer area nodes, injection of characteristic current, and synchronous collection of response waveforms; signal preprocessing: separating a key frequency band through double-digital band-pass filtering, and calculating energy ratio and other enhanced fault features; performing multi-source feature fusion and intelligent diagnosis, constructing a vector containing statistical features, time domain distortion features and topology identification, and inputting a gradient boosting decision tree and deep neural network hybrid model to obtain fault confidence and type; and based on fault positioning and verification of topology, scheduling multi-node cooperative monitoring, and determining a fault point in combination with a topological relation. The method improves the data reliability and diagnosis precision, achieves the precise positioning of a fault, and guarantees the safe operation of a power distribution network.

The invention discloses a method and system for predicting juvenile depression based on intestinal flora, and relates to the technical field of bioinformatics and artificial intelligence, and the method comprises the steps: firstly, obtaining an original sequence of a microbiome, carrying out the preprocessing of the original sequence of the microbiome, and obtaining a feature matrix; and screening core flora characteristics with stable trans-folding by adopting characteristic importance evaluation and interpretability analysis based on a gradient boosting decision tree. A mixed weighted graph is constructed based on Spearman correlation and a proximity relationship, and an absolute value of a correlation coefficient is taken as an edge weight and an edge density is adjusted through a threshold adaptive strategy. And finally, through an improved graph attention neural network, based on edge weight attention, layer normalization and random inactivation, enhancing robustness, and adopting adaptive optimization to complete parameter learning. And determining a dynamic classification threshold according to the AUC of the target patient, and outputting a sample discrimination result and confidence. According to the method, the accuracy, stability and biological interpretability of juvenile depression recognition are remarkably improved.

The invention discloses a power distribution network transient characteristic prediction method based on supervised learning, and relates to the technical field of power distribution network state prediction, and the method comprises the steps: collecting historical operation data through a power distribution network monitoring system, carrying out the data preprocessing, and obtaining standardized multi-dimensional time series data; carrying out transient feature extraction, constructing a high-dimensional feature set, and carrying out feature dimension reduction according to a transient event tag to generate a feature subset; inputting the feature subset into a mixed supervised learning model of a gradient boosting decision tree GBDT and a long short-term memory network LSTM for joint training to obtain a transient feature prediction result; and calculating a root-mean-square error according to the transient characteristic prediction result and the real-time monitoring observation value of the power distribution network, and dynamically adjusting hyper-parameters of the supervised learning model based on a Bayesian optimization algorithm. According to the method, the detection accuracy can be improved, the calculation complexity can be reduced, and the discrimination capability and the time sequence prediction capability of the model are considered.

The invention belongs to the field of cultural heritage digital protection, and discloses an ancient building three-dimensional modeling method based on three-dimensional laser scanning, which comprises the steps of extracting feature points of a point cloud data set and texture image data, and performing registration in combination with a flight log of an unmanned aerial vehicle; performing image restoration and feature extraction on the texture image data and the point cloud-image registration result through a convolutional neural network-probability Markov random field (CNN-PMRF) model; performing geometric feature extraction on the point cloud data set, fusing the texture image feature vector to obtain a geometric-texture joint feature vector, and optimizing a rough mesh model generated based on the point cloud data set; mapping the repaired texture image data to the optimized grid model to obtain a preliminary three-dimensional grid model; and processing the preliminary model parameters through a gradient boosting decision tree (GBDT) model to obtain a correction value, and adjusting the preliminary three-dimensional grid model based on the correction value to obtain an optimal three-dimensional model. The precision of three-dimensional modeling of the ancient building can be improved.

The invention discloses a thermal power generating unit decommissioning path planning method and device based on meteorological and hydrological risks, equipment, a medium and a product, and relates to the field of power system decision optimization. The method comprises the steps of obtaining meteorological and hydrological risk data and a decommissioning index of a thermal power generating unit; according to the decommissioning index and the meteorological and hydrological risk data under the climate change, a progressive hierarchical screening logic method is adopted for screening and constraint progressive correction processing; performing mapping and nonlinear correlation interaction analysis by adopting Monte Carlo simulation and a gradient boosting decision tree and combining multiple groups of parameter combination data, such as water temperature and runoff volume in meteorological and hydrological variables; and performing collaborative optimization processing based on the adaptive strategy model and a set analysis function to obtain an optimal strategy, and then performing mapping and analysis processing in combination with an analysis result to obtain targeted strategy list information for planning the decommissioning path of the thermal power generating unit. The invention aims to realize the planning of the decommissioning path of the thermal power generating unit.

The invention relates to the technical field of intelligent replenishment of catering stores, and discloses an intelligent replenishment method and system for catering stores, and the method comprises the steps: constructing a prediction model based on a gradient boosting decision tree algorithm, constructing brand training data with stores as granularity, constructing a feature project, carrying out the feature screening, and training the prediction model; the method comprises the following steps: constructing a sample set based on stores and materials, obtaining an inventory unit of the last order of the sample set, calculating a replenishment period and a sales amount in a sales starting period, and calculating a thousand yuan amount through the inventory unit, the replenishment period and the sales amount; receiving a replenishment order-placing instruction, inputting a replenishment time range into the trained prediction model, calculating to obtain an estimated turnover of a specified time range part, predicting the consumption of each item in the time range, calculating the actually required replenishment amount, and sending the replenishment amount to the prediction model; and a method combining data analysis and artificial intelligence algorithm prediction is adopted to improve the replenishment management problem of the catering store.

The invention discloses an urban rail transit energy management method based on multi-source fusion, and the method comprises the steps: employing a support vector machine algorithm to analyze a correlation mode between train intensive operation and passenger flow surge according to an obtained energy demand fluctuation index, and determining a potential energy consumption peak value position; the determined adjustment parameters are obtained, a power supply system control instruction is updated in combination with real-time train track information, and dynamic power supply load configuration is obtained; whether the obtained dynamic power supply load configuration is matched with the current passenger flow surge data or not is judged, if yes, a mode switching signal is sent to an equipment controller, and energy use feedback data after execution is obtained; according to the obtained energy use feedback data, evaluating the response accuracy of the system integration effect to demand fluctuation by adopting a gradient boosting decision tree algorithm, and determining further trajectory optimization suggestions; and updating a train operation scheduling model through the determined trajectory optimization suggestion to obtain an integrated multi-source information linkage mechanism.

The invention discloses a heterogeneous unmanned aerial vehicle cooperative operation air safety assessment method, and relates to the technical field of unmanned aerial vehicle cooperative operation safety, and the method comprises the steps: obtaining static parameters and operation dynamic parameters of a heterogeneous unmanned aerial vehicle; constructing a dynamic and static parameter incidence matrix based on a gradient lifting decision tree algorithm; constructing a positioning precision probability matrix based on Bayesian updating; task and operation dynamic data are collected in real time; in combination with the environment interference coefficient and the task priority weight, collision time prediction is optimized by using LSTM, and the air collision probability is calculated; and triggering the graded security risk alarm. According to the invention, refined quantitative evaluation and graded early warning of safety risks in a heterogeneous unmanned aerial vehicle cooperative scene are realized, and the problems of extensive evaluation and insufficient collaboration in the prior art are solved.

The invention discloses a method for predicting the mechanical property of a dissimilar metal friction stir lap joint welded joint by fusing physical information, and belongs to the technical field of crossing of material processing and artificial intelligence. The method comprises the following steps that firstly, welding samples under different technological parameters are prepared through experiments, and the mechanical properties of the welding samples are tested; meanwhile, establishing a finite element simulation model, and extracting physical field data such as a temperature field and a stress-strain field; fusing the process parameters and the physical field data to serve as input features, taking the measured mechanical property data as output features, and forming a machine learning training data set; a prediction model is trained by adopting algorithms such as a gradient lifting decision tree and limit gradient lifting; and finally, new process parameters and physical field data obtained through finite element simulation are input, and the mechanical property of the joint can be efficiently and precisely predicted through the model. According to the method, the defects that a traditional trial and error method is high in cost and long in period are overcome, and key technical support is provided for optimization and intelligent design of the dissimilar metal friction stir lap welding process.

The invention discloses an intelligent fire-fighting equipment fault prediction method, and belongs to the technical field of intelligent maintenance of fire-fighting equipment. According to the method, pressure, electrical waveform and environmental data are dynamically acquired through a multi-source sensor, spatial-temporal features are extracted in parallel by adopting a bidirectional LSTM and a multi-scale convolutional network, and feature fusion is realized by utilizing a cross-modal attention mechanism; outputting a fault probability based on a gradient boosting decision tree model, and predicting the remaining service life in combination with Bayesian regression; the firmware upgrading authority is controlled through a health degree dynamic scoring system, and the upgrading safety is guaranteed through AES-256-CBC encryption and SM3 signature verification; and generating an optimal maintenance path based on an improved genetic algorithm, and scheduling an engine to respond to a sudden fault in real time. Tests show that the fault early warning accuracy rate reaches 93.1%, the maintenance cost is reduced by 45%, the upgrade failure blocking rate is 100%, and the intelligent level and reliability of operation and maintenance of the fire-fighting equipment are remarkably improved.

The invention discloses a river and lake backflow recognition and driving mechanism analysis method based on interpretable machine learning, and relates to the technical field of hydrology and water resource analysis and artificial intelligence application, and the method comprises the steps: collecting long-sequence hydrology data of a river and lake system; taking operation nodes of the large hydro-junction project as boundaries, and dividing the time sequence into different characteristic periods; constructing a multi-dimensional input feature set; a class weight balance strategy and a Bayesian optimization algorithm are adopted to train a backward flow recognition model based on a gradient lifting decision tree; a marginal contribution value of each hydrological driving factor is calculated by using an SHAP interpretability method, a physical threshold for inducing backward flow is identified by combining an SHAP dependency graph with a binary box plot, analysis results in different periods are compared, and an evolution rule of a backward flow driving mechanism is revealed. The method effectively solves the problems that a traditional method is difficult to capture nonlinear hydrological response and the black box model lacks physical mechanism explanation, and can accurately recognize the backward flow event.

The invention discloses a silicon nitride ceramic thermal conductivity prediction method based on machine learning coding-free feature processing. The method comprises the following steps: acquiring a data set; declaring a chemical character string field of the sintering aid as a disordered data type, and preprocessing other numerical characteristics at the same time; keeping the field of the sintering aid as a disordered data type, and preprocessing other numerical values; selecting a gradient lifting decision tree model supporting native processing category features as a prediction model and performing optimization; a to-be-predicted formula-process parameter combination is input into the optimized prediction model, a thermal conductivity prediction value is output in real time, and the to-be-predicted formula-process parameter combination is directly input into the model through an original chemical formula character string. The invention further discloses a device for implementing the method, computer equipment and a readable storage medium. According to the invention, the original chemical formula of the sintering aid can be directly utilized, and the thermal conductivity can be predicted within millisecond response time without any code conversion.

The invention provides a high geothermal exploitation land subsidence data monitoring method and device. The method comprises the following steps that S1, a monitoring area is determined, and monitoring points are arranged; s2, corresponding monitoring devices are installed at the monitoring points and debugged; s3, collecting multi-source original data; s4, preprocessing the multi-source original data; s5, constructing a collaborative fusion model of the long short-term memory network and the gradient boosting decision tree, and outputting a final fusion settlement amount; and S6, carrying out time sequence analysis, spatial distribution analysis and anomaly judgment. Through the full-process design of multi-source data acquisition, intelligent fusion modeling and dynamic analysis early warning, high-precision and dynamic settlement monitoring is achieved, the problems of precision limitation and response lag of a traditional monitoring method are solved, and key technical support is provided for safe and sustainable development of high geothermal resources.

The disclosed embodiments include computer-implemented apparatuses and processes that dynamically predict future occurrences of events using adaptively trained artificial-intelligence processes and contextual data. For example, an apparatus may generate an input dataset based on first interaction data and contextual data associated with a prior temporal interval, and may apply an adaptively trained, gradient-boosted, decision-tree process to the input dataset. Based on the application of the adaptively trained, gradient-boosted, decision-tree process to the input dataset, the apparatus may generate output data representative of a predicted likelihood of an occurrence of an event during a future temporal interval, which may be separated from the prior temporal interval by a corresponding buffer interval. The apparatus may also transmit a portion of the generated output data to a computing system, and the computing system may be configured to generate or modify second interaction data based on the portion of the output data.

According to the photovoltaic power generation prediction system and method based on the smart power grid provided by the invention, the efficient fitting advantage of a gradient boosting decision tree model on high-dimensional static characteristics is utilized under a long-period stable weather condition, and the capturing capability of a long-short-term memory network on time sequence nonlinear dynamics is fully exerted in a weather sudden change period; weather categories are judged in real time and weights are dynamically adjusted through an environmental condition classifier, so that the RMSE of a final prediction result in four typical scenes of sunny days, cloudy days, cloudy days and rainy days is obviously reduced, and the RMSE is obviously superior to that of an existing fixed weight combination model; meanwhile, through an automatic data cleaning chain formed by an isolation forest and Lagrange interpolation, the data anomaly rate is controlled to be 0.1% or below, and the dimensional difference is eliminated by adopting minimum-maximum standardization, so that the model training stability is ensured; the parallel hybrid architecture realizes minute-level rolling prediction under the acceleration of the GPU, and the real-time requirement of a provincial power grid dispatching center is met.

The invention provides a multi-dimensional data preferential analysis method and device based on a gradient boosting decision tree model, and relates to the technical field of data mining, in the method, a target gradient boosting decision tree model is adopted, the nonlinear modeling problem of strategy optimization in multi-dimensional data is solved, and the multi-dimensional data is optimized according to the target weight determined in the training process. According to the method, key features can be accurately identified, the processing efficiency and precision are high, compared with a traditional linear regression or single decision tree method, the accuracy and real-time performance of strategy optimization can be improved, high interpretability and robustness are achieved, an optimization strategy can be adjusted in a self-adaptive mode in a changeable environment, and the method is suitable for popularization and application. The method is widely applied to multiple fields of industrial optimization, intelligent decision making and the like.

The invention relates to an injection molding product quality prediction method based on a random forest algorithm. The method comprises a model training stage and a prediction stage. The model training stage comprises the following steps: acquiring a historical data set, wherein the historical data set comprises a process parameter set and a corresponding product quality label; performing principal component analysis on the historical data to obtain a principal component set and a first transformation matrix; screening the principal component set through a gradient lifting decision tree algorithm; training the random forest prediction model by using the sample data set; the prediction stage comprises the following steps: collecting a process parameter set in a production process of a to-be-predicted product; performing transformation and screening; and predicting the product quality by using the trained random forest prediction model. According to the invention, a prediction model having significant advantages in the aspects of data dimension reduction, feature selection and nonlinear data processing can be provided, the accuracy of quality prediction of the injection product is improved, and the processing quality of the injection product is improved in the aspect of improving real-time process parameters.

The disclosed embodiments include computer-implemented apparatuses and processes that dynamically predict future occurrences of events using adaptively trained artificial-intelligence processes and contextual data. For example, an apparatus may generate an input dataset based on first interaction data and contextual data associated with a prior temporal interval, and may apply an adaptively trained, gradient-boosted, decision-tree process to the input dataset. Based on the application of the adaptively trained, gradient-boosted, decision-tree process to the input dataset, the apparatus may generate output data representative of a predicted likelihood of an occurrence of an event during a future temporal interval, which may be separated from the prior temporal interval by a corresponding buffer interval. The apparatus may also transmit a portion of the generated output data to a computing system, and the computing system may be configured to generate or modify second interaction data based on the portion of the output data.

The invention discloses a diamond milling cutter on-machine wear state prediction method and system based on machine learning, and belongs to the technical field of wear prediction. Comprising a baseline signal template acquisition module, a representation data acquisition module, a defect feature extraction module, an image feature extraction module and a wear state output module. According to the method, the visual quality confidence is generated through image quality evaluation, and the influence of a low-quality image is automatically weakened, so that the model is more dependent on a residual signal; a simulation defect signal is superposed on a baseline signal template to generate a synthetic residual signal, training samples are added, a lightweight gradient boosting decision tree model is adopted to reduce the computing power requirement, real-time monitoring on weak computing power equipment is realized, and the problem that in the prior art, due to the need of a large amount of training data, high computing power and a clean imaging environment, the cost is low is solved. And the problems of difficulty in landing and high cost caused by direct conflict with small-batch, weak-computing-power and high-oil-mist conditions of a woodworking tool manufacturing workshop are solved.

The invention discloses an advertisement design display system and method based on big data. The system comprises a data acquisition layer for acquiring multi-source data sources; the semantic understanding layer is used for generating semantic vectors of search words and advertising words based on a BERT-Chine pre-training language model, calculating a quantitative semantic matching degree through cosine similarity, performing deep semantic understanding and synonym equivalence matching, performing intention classification on features through an XGBoost gradient promotion decision tree, and judging that a user is in an instant purchase, decision period or interest exploration state; the scene sensing layer is used for dynamically recognizing a scene where a user is located by using an LSTM-CRF time sequence model; the feature recombination layer is used for extracting explicit features and mining implicit correlation features; the deep matching layer is used for generating a comprehensive matching score of a 0-1 interval by fusing explicit features and implicit association features in combination with multi-task learning, and performing screening according to the comprehensive matching score; the value measurement layer is used for quantifying contributions of different advertisement contacts to final conversion; and the execution layer is used for carrying out advertisement rendering and putting.

The invention relates to a lignocellulose biomass glucose production prediction method based on machine learning, and aims to improve the yield of glucose and optimize a biomass conversion process. According to the method, machine learning models such as a multi-layer perceptron, support vector regression, a random forest, a gradient boosting decision tree and a convolutional neural network are adopted to predict the LCB glucose yield processed by different preprocessing modes. Experimental results show that the convolutional neural network model is optimal in performance, the decision coefficient Rreaches up to 0.95, and the method has excellent generalization ability and prediction precision. The prediction precision is remarkably improved by feature extraction and principal component analysis in the model establishment process, and the Rof the convolutional neural network model is improved from 0.76 to 0.95. The efficient and accurate prediction method is provided for optimization of the biomass saccharification process, the method can be widely applied to the field of biological energy, and technical support is provided for improving the resource utilization efficiency of lignocellulose biomass.