101 results about "Bayesian fusion" patented technology

The invention discloses a thunder and lightning monitoring and early warning method and system based on multi-source data fusion, and relates to the technical field of thunder and lightning early warning, and the method comprises the steps: extracting electric field time domain and frequency domain features, magnetic field change features, lightning activity modes and meteorological change features through obtaining atmospheric electric field, magnetic field, lightning activity and meteorological environment data in real time; and constructing multi-source feature data. A time sequence analysis and Bayesian fusion technology is adopted to calculate a correlation weight between data sources, and a fusion feature vector is generated. And establishing a weighted regression model based on the vector, calculating thunder and lightning occurrence probability through dynamic weight distribution, and generating a risk distribution map in combination with geographic information. The method has a closed-loop feedback optimization mechanism, model parameters and weights can be adaptively adjusted according to prediction errors and early warning accuracy, the accuracy, timeliness and environmental adaptability of lightning early warning are improved, and the method is widely applied to the fields of electric power, aviation, buildings and the like.

The invention belongs to the technical field of bridge monitoring, and relates to a system and a method for fusing multi-source data of a bridge structure. Comprising a heterogeneous topological graph construction and manifold embedding technology module, a multi-scale space-time cognitive convolutional neural network module, a continuous manifold space-time alignment and Bayesian fusion module and a structure health index calculation and state evaluation module. The heterogeneous topological graph construction and manifold embedding technology module is used for obtaining a heterogeneous topological graph, a node embedding vector and a manifold model parameter; the multi-scale space-time cognitive convolutional neural network module is used for performing deep feature extraction on the heterogeneous topological graph to obtain multi-scale fusion features; the continuous manifold space-time alignment and Bayesian fusion module is used for obtaining space-time alignment parameters and fusion state vectors; the structure health index calculation and state evaluation module is used for carrying out structure health monitoring and state evaluation on the bridge to obtain a final health evaluation result; therefore, the intelligence, automation and reliability levels of the structure monitoring system are improved.

The invention relates to the technical field of safety management and risk assessment, and discloses a laboratory safety intelligent monitoring and early warning method and system, and the method comprises the following steps: S1, building a three-dimensional digital model of a laboratory; s2, deploying a sensor network covering a laboratory; s3, monitoring an operation behavior in real time through a sensor network, and comparing the operation behavior with the operation logic chain; s4, when the sensor network detects that the physical environment is abnormal; s5, collaborating the logic abnormal state, the position and strength of the risk source and the risk type; and S6, performing evolution prediction based on the risk type and the risk source. According to the method, Bayesian fusion reasoning is performed on context information such as multi-dimensional sensor evidence and real-time operation regulations, so that high-precision and high-confidence identification of risk types is realized, and the problem that the risk types cannot be identified due to lack of cognition on field operation activities is solved. And the risk qualitative is fuzzy, the false alarm rate is high, and the real dangerous case and compliance operation interference cannot be distinguished.

The invention provides an exoskeleton mountaineering intention recognition method and system and a storage medium, and belongs to the technical field of exoskeleton robot control, and the method comprises the steps of signal preprocessing and compensation, hierarchical feature extraction, multi-modal fusion recognition, control output, safety protection and the like. The method comprises the following steps: performing 50Hz power frequency filtering and 20-450Hz band-pass filtering on an electromyographic signal, and compensating signal distortion caused by muscle deformation by combining IMU (Inertial Measurement Unit) acceleration data; a dynamic four-dimensional channel is adopted to preferably extract myoelectricity features, and an improved attention mechanism model is utilized to extract multi-scale features; fusing multi-modal information such as myoelectricity and terrains based on a Bayesian fusion framework to realize intention recognition; meanwhile, triple safety protection strategies of joint angle hard limiting, falling detection and protection and signal loss fault-tolerant processing are set; the accuracy and control speed of motion intention recognition are improved, good safety performance is achieved, and the auxiliary effect and reliability of the exoskeleton in the mountaineering motion are effectively improved.

The invention discloses an intelligent fishing point dynamic prediction method and system based on multi-source marine environment data fusion. The method comprises the following steps: step 1, access, space-time alignment and pre-screening of multi-source heterogeneous marine environment data; step 2, priori knowledge base construction and suitability modeling based on target fish ecological habits; 3, constructing a fishing point prediction model fusing the multi-time-sequence environmental characteristics and deep learning; step 4, fusing two-channel prediction results under the Bayesian framework and quantifying uncertainty; 5, generating a dynamic mask of a real-time sea condition safety threshold value and fishery regulation space constraint; 6.1, constructing a comprehensive scoring function of the risk perception function. According to the method, multi-source heterogeneous data is constructed, a target fish ecological suitability model and a depth time sequence prediction model are combined, the fishing point posterior probability is generated through a Bayesian fusion mechanism, the prediction uncertainty is quantified, and dynamic fishing point recommendation with risk perception and compliance safety is realized.

The invention relates to the technical field of automobile electronics and intelligent control, and discloses an intelligent cabin mechanical arm system which comprises a folding mechanical arm body, a tail end sensing interaction module, a driver state monitoring subsystem and a central control unit which are installed in a cabin. The central control unit controls the storage or working mode of the mechanical arm according to the comprehensive fatigue index of the driver; in the working mode, visual gazing information is used as a gating signal to activate electroencephalogram analysis, the operation intention is confirmed in combination with the visual prior probability and electroencephalogram signals, and the mechanical arm impedance parameters are adjusted in real time based on the fatigue state. According to the method, through Bayesian fusion of vision and electroencephalogram signals, the problem that single-mode control is unstable is solved; by means of variable impedance control and collision detection of the momentum observer, active safety protection based on the physiological state of the driver is achieved, and non-sensitive and high-safety intelligent auxiliary experience is provided in a limited cabin space.

The invention relates to the technical field of information security, in particular to a network security event association detection method based on big data analysis. Comprising the following steps: data acquisition; feature extraction and fusion; correlation detection is carried out, wherein an improved Apriori-Bayesian fusion algorithm is adopted, and discretization processing is carried out on the event feature vectors; mining a frequent item set by using an improved Apriori algorithm; and risk assessment and result output. According to the method, an improved Apriori-Bayesian fusion algorithm is adopted, discretization processing is carried out on event feature vectors according to types, meanwhile, a security event weight factor is introduced to calculate the item set weighted support degree, and a minimum support degree threshold value is dynamically adjusted to mine a frequent item set; the association confidence coefficient is calculated in combination with the Bayesian network, and the confidence coefficient is corrected through the space-time association coefficient, so that the association relationship between the network security events can be scientifically judged, the problems of limited association judgment accuracy and lack of quantitative correction in the traditional technology are solved, and the association false alarm and missing report probability is reduced.

The invention relates to the technical field of charging pile intelligent scheduling, and discloses a multi-model power transmission line channel three-dimensional fusion method, system and device based on BDF Bayesian data fusion and a medium, and the method comprises the steps: obtaining multi-source power transmission line data; performing data fusion on the registered multi-source data through a BDF Bayesian fusion strategy; generating a three-dimensional fusion model of the power transmission line channel; constructing a three-dimensional grid model, and carrying out object recognition through a deep learning algorithm to obtain various obstacles in the power transmission line channel; and constructing a multi-factor weighted scoring model in combination with the geometric features of the obstacles and meteorological data to obtain risk scores of the obstacles and perform hidden danger analysis. When data in a complex environment is processed, data inconsistency and noise interference are overcome, and the precision and robustness of the model are improved; the method effectively processes data changes in a dynamic environment, and adapts to various change factors in a complex scene.

The invention discloses a multi-source three-dimensional geological data fusion and management method and related equipment, and relates to the technical field of geological information, and the method comprises the steps: obtaining standardized geological data; fusing the standardized geological data based on a Bayesian fusion framework; constructing a multi-scale three-dimensional geologic model by adopting a potential field interpolation method based on probability constraints provided by posterior probability distribution; performing uncertainty quantification on the multi-scale three-dimensional geologic model by adopting a Monte Carlo simulation method; and storing the multi-scale three-dimensional geologic model and the uncertainty quantification result to a data management platform conforming to an OGC standard, and providing visualization, query and access of a geologic map layer through a Web service interface. According to the method, the sharing efficiency, the reuse value and the application convenience of the geological result data are greatly improved, and the intelligent level and the decision support capability of geological data analysis are enhanced on the whole.

The invention discloses a geological settlement monitoring method and system fusing deep learning and multi-source data, and relates to the technical field of geological settlement, and the method comprises the steps: collecting multi-source settlement observation and driving data, generating a settlement risk area mask based on historical records, and carrying out the self-adaptive grid division; a multi-source settlement field is generated through Kriging interpolation, and a driving factor grid field is mapped; performing spatial pyramid and time multi-scale decomposition on the settlement field and the driving factor to obtain a time-space sub-band; performing Bayesian fusion based on the sub-band confidence weight to obtain a fusion settlement field; inputting the fusion field and the driving factor into a deep learning model to train a multi-scale prediction sub-model, and reconstructing a global continuous settlement prediction field through cross-scale consistency; and dynamically optimizing the risk mask and the grid according to a prediction result to realize iterative monitoring. The problems of difficulty in multi-source data fusion, spatial scale heterogeneity and difficulty in accurate prediction of local high-risk area settlement in geological settlement monitoring are solved.

The invention discloses an underground packer coupling integrity diagnosis system and a digital twinborn life prediction method. The system comprises a data acquisition layer, an edge computing layer, a cloud analysis layer with a built-in L4-level digital twin system and an application layer which are connected in sequence. According to the method, vibration, corrosion and other parameters are collected through a sensor, after preprocessing of an edge layer, a cloud calls a three-field coupling dynamic model, multi-field parameters, the failure probability and the remaining life are calculated in combination with an LSTM and Bayesian fusion algorithm, and an application layer outputs diagnosis results and maintenance suggestions and forms a closed loop. The problems that traditional methods depend on experience, multi-field coupling is difficult to quantify and the digital twinborn level is low are solved, the maintenance cost can be reduced, the well control accident risk is reduced, and a key technical support is provided for predictive maintenance of an oil and gas well.

The invention relates to the technical field of energy storage battery management, and provides an energy storage battery management system based on Bayesian fusion and model prediction control, and the system comprises a data collection and preprocessing module which collects the voltage, current and temperature data of an energy storage battery pack in real time; the electrochemical model prediction module is used for updating parameters by adopting a recursive least square method based on a second-order RC equivalent circuit model to obtain a capacity prediction value and prediction uncertainty; the data driving model prediction module is used for obtaining a capacity prediction value and prediction uncertainty through Monte Carlo dropout reasoning; the Bayesian fusion module is used for calculating an evidence weight based on the prediction uncertainty and carrying out Bayesian fusion on the capacity prediction value; and the model prediction control module is used for solving an optimal equalization strategy based on the fusion capacity prediction value and generating a control instruction to realize intelligent equalization scheduling of the energy storage battery pack. According to the invention, the accuracy of energy storage battery capacity prediction is improved, and adaptive battery management under complex working conditions is realized.

The invention relates to a plateau energy storage battery monitoring method and system based on physical data dual drive, and the method comprises the steps: firstly constructing a battery internal resistance physical model considering plateau environment correction, predicting the internal resistance in real time, and generating a failure prior probability; meanwhile, a support vector machine (SVM) and a random forest (RF) are used for constructing a data driving model, battery operation characteristics are extracted, and fault probability and uncertainty are output. On the basis, a Bayesian fusion method is used, the weights of a physical model and a data driving model are dynamically adjusted, the battery failure posterior probability is calculated, and the total uncertainty is quantified. And finally, setting a decision threshold, and when the posterior probability exceeds the threshold, triggering early warning and taking protection measures. The method effectively fuses the theoretical advantages of a physical model and the actual data mining capability of a data driving model, adapts to the plateau environment, and provides guarantee for safe and stable operation of the energy storage battery of the plateau photovoltaic power station.

The invention provides a Bayesian fusion-based 4D millimeter wave radar point cloud enhancement and target detection method, and the method comprises the steps: 1, projecting a 4D millimeter wave radar point cloud to an image plane, carrying out the matching of an image instance segmentation result, and obtaining an image semantic category and image segmentation confidence; 2, constructing a class conditional probability density model based on the physical characteristics of the radar points; based on a Bayesian probability framework, carrying out weighted fusion on the image segmentation confidence and the class probability density to obtain fusion confidence; 3, taking the fusion confidence and semantic category codes as augmented features, and performing feature splicing on the augmented features and the 4D millimeter-wave radar point cloud to generate a semantic enhanced point cloud; and sampling the semantic enhanced point cloud by adopting a sampling method fusing confidence guidance, and inputting the sampled semantic enhanced point cloud into a detection network for training and reasoning. According to the method, the technical problems of unidirectional dependence, shallow geometric matching and insufficient utilization of radar physical characteristics in the existing image and radar point cloud fusion technology are solved.

The invention discloses a dynamic task unloading method and system based on multi-dimensional perception, and relates to the technical field of edge computing and cloud computing collaborative optimization, and the method comprises the steps: carrying out the real-time monitoring of four key states of communication, computing power, energy consumption and environment of an intelligent video monitoring task of an intelligent construction site, and constructing a comprehensive unloading judgment system; respectively calculating a communication stability coefficient, a computing power congestion coefficient, an energy consumption cost coefficient and an environment perturbation sensitivity coefficient, performing evaluation, and automatically generating labels such as communication abnormity high risk, computing power insufficiency, energy consumption disqualification and environment perturbation; and then multi-source state comprehensive judgment is realized based on weighted Bayesian fusion, short-time resource trend prediction is carried out in combination with a lightweight GRU model, and finally, local, neighborhood and cross-domain optimal unloading decisions are formed. According to the method, intelligent switching of task unloading can be realized in a dynamic and sudden interference construction site environment, and the execution stability, the resource utilization efficiency and the energy consumption control capability of a video monitoring task are improved.

The invention discloses a narrow-body self-walking operation platform battery pack charging control method, and belongs to the technical field of battery management. Operating parameters of a lithium battery pack and working condition parameters of a working platform are collected in real time, corresponding charging stages are selected according to charge states and working condition types, and the charging process is divided into five stages including pre-charging, quick charging, optimized charging, equalizing charging and floating charging maintenance. A three-dimensional temperature field model is established based on multi-point temperature data, and a comprehensive temperature compensation coefficient is calculated to accurately adjust the charging current. The state of charge and the state of health of the battery are jointly estimated by adopting extended Kalman filtering and a long-short term memory neural network, and the estimation precision is improved through Bayesian fusion. The inclination angle and vibration acceleration of the platform are monitored in real time, and charging is adjusted or stopped according to safety conditions. The charging time is remarkably shortened, the charging efficiency is improved, the battery temperature rise is reduced, the battery cycle life is prolonged, and meanwhile the energy utilization efficiency and safety of the operation platform are improved.

The invention discloses an unmanned aerial vehicle load target tracking system and method based on multi-sensor fusion, and the method comprises the steps: obtaining visible light, infrared and laser radar data, carrying out the time sequence synchronization and attitude calibration, and obtaining a target fusion estimation value through a dynamic weighting Bayesian fusion algorithm; the improved Siamese neural network is used for feature matching, the LSTM trajectory predictor is combined to output a short-term motion state, and finally the adaptive mechanical control module drives the holder to realize stable tracking. According to the invention, the robustness, precision and continuity of target tracking in a complex environment are effectively improved.

The invention provides an operation state prediction method and system for a distribution network backup power supply. The running state prediction method of the distribution network backup power supply comprises the following steps: acquiring various target power supply parameters in real time, and performing fusion processing on the various target power supply parameters by adopting a Bayesian fusion algorithm to obtain a posterior decision probability; predicting working condition data of the distribution network backup power supply based on the target power supply parameter and the posterior decision probability; and further predicting the future operation state of the distribution network backup power supply according to the working condition data and outputting a prediction result. According to the method, the operation information of the distribution network backup power supply can be comprehensively acquired, association and uncertainty among various parameters are considered, dynamic computing power support can be carried out under different working conditions, and the future operation state of the backup power supply can be evaluated more comprehensively and accurately; besides, dynamic changes of various factors are considered, so that configuration, dynamic management and self-healing processing of the backup power supply are more scientific, and the problem of resource waste or insufficient power supply is avoided.

The invention discloses a bidirectional information retrieval enhancement generation method for a large language model, and belongs to the technical field of artificial intelligence. In order to overcome the defects that noise is introduced and key evidences are omitted due to the fact that traditional RAG only executes'query-document 'one-way retrieval, a two-way semantic perception retrieval enhancement generation model and a two-stage training framework are constructed, wherein in the first stage, the positive / negative example distance is increased in an embedded space in a contrast learning self-supervision mode; in the second stage, fine-grained correlation discrimination is carried out on query-document bidirectional sentences through supervised dichotomy, and probabilistic correlation scores are output; in the reasoning stage, the bidirectional probabilities are fused according to Bayesian to obtain final relevancy, document reordering is carried out, and plug and play can be achieved without fine adjustment of LLM in the whole process. According to the method, the accuracy and consistency of single-hop and multi-hop questions and answers and fact checking tasks are remarkably improved, and the method has the advantages of light weight and low deployment cost.

The invention discloses an unmanned aerial vehicle visual navigation method based on infrared semantic feature matching and inter-frame anchoring, and aims at the core requirement of unmanned aerial vehicle autonomous navigation in a GNSS denial environment, the stability of infrared imaging and the robustness of high-level semantic features are fully combined, and the high-precision, continuous and stable visual autonomous navigation capability is realized. The method is especially suitable for complex scenes such as low-illumination, weak-texture and large-area homogenized areas at night. Through innovation in the aspects of infrared semantic map construction, deep semantic feature extraction, multi-scale semantic matching, semantic anchoring key frame selection, inter-frame recursion positioning and closed-loop correction, Bayesian fusion estimation longitude and latitude solution and the like, the positioning precision and robustness of the unmanned aerial vehicle in GNSS denial, low-visibility and large-area homogeneous scenes are remarkably improved.

The invention discloses a zoning collaborative air pollution monitoring method and system, and the method comprises the steps: obtaining multi-source basic data of a monitoring region, calculating a pollution risk index and an attention index, and carrying out the weighting, thereby obtaining a comprehensive priority; dividing into sub-regions of different levels according to the priority, and configuring devices of different types or sensitivities to form a monitoring network; gas concentration and video image data are collected, pollution event comprehensive confidence is generated through fusion analysis, and when the pollution event comprehensive confidence exceeds a threshold value, a pollution event is judged and early warning is performed; the pollutant diffusion trend is predicted based on early warning, and a linkage control instruction for the treatment equipment is automatically generated; a two-factor dynamic partition model fusing pollution risks and regional attention is constructed, and a Bayesian fusion judgment algorithm that only results can be recognized by gas sensing data and videos is combined, so that complete closed-loop control from intelligent point distribution, accurate sensing and traceability prediction to automatic linkage is formed; and the overall efficiency and sustainability of regional pollution prevention and control are remarkably improved.

The invention discloses a contribution decomposition calculation method for lake expansion. The contribution decomposition calculation method comprises the following steps: extracting a lake area through a remote sensing image and a digital elevation model, inverting water volume change, judging a rainfall phase state by using a temperature threshold method, estimating ice and snow ablation amount in combination with a degree-day factor method, and calculating a glacier runoff total amount; constructing a single-layer evaporation model, calculating flux of net radiation, sensible heat, latent heat, water body heat storage and the like based on a lake surface energy balance equation, and obtaining daily lake surface evaporation capacity; quantile mapping and Bayesian fusion are combined, and lake surface rainfall is corrected; non-glacial runoff is calculated according to a lake water balance equation; dividing a stable period and an expansion period according to the lake area trend, calculating an abnormal value of the expansion period by taking the hydrological mean value of the stable period as a reference, and finally determining the expansion contribution of each hydrological factor according to the increment proportion of the abnormal value in the total water quantity. Through the method, the contribution intensity of different driving factors is determined, scientific support is provided for lake change simulation and evolution prediction, and ecological protection and management strategies are more targeted.

The invention relates to the technical field of main power distribution network monitoring, in particular to a main power distribution network integrated dispatching monitoring method and system, and the system achieves main power distribution network integrated dispatching monitoring through the method steps of main network and distribution network data acquisition, data preprocessing, data fusion, main power distribution network fusion topology model establishment and the like. When the operation data of the main power distribution network is fused, the traditional Bayesian fusion algorithm is improved by using a confidence factor, so that the heterogeneous data sources can be more effectively integrated, and more accurate information is provided for the operation and maintenance of the main power distribution network; the fused state estimation value reflects the most probable value of the state parameter of the main power distribution network under the condition that all observation data and priori knowledge are given, the information of all data sources is integrated, and the reliability of different data sources is constrained through confidence factors, so that the state estimation value is more accurate and reliable.

The application belongs to the technical field of material performance prediction and uncertainty analysis, and proposes a beryllium aluminum alloy performance uncertainty quantification method based on Bayesian ensemble learning, which is innovative in constructing and training multiple independent performance prediction models to form the basis of ensemble learning. After the training of each model is completed, a performance prediction value can be output for a new input sample. After obtaining the prediction outputs of multiple independent models, a Bayesian fusion method is used to comprehensively process the prediction results on the probability level to obtain the fused performance prediction distribution; and the complete results of the beryllium aluminum alloy performance prediction are output in a clear, intuitive and convenient engineering application format. The application has the advantages that the robustness and generalization ability of the prediction results are improved, a decision basis is provided for material performance evaluation, and good adaptability is achieved for the case of limited data quantity, and important innovations are achieved in the aspects of material performance uncertainty quantification theory and engineering application.

The application discloses a lake expansion contribution decomposition calculation method, extracts lake area and reverses water quantity change through remote sensing image and digital elevation model, discriminates precipitation phase state by using a temperature threshold method, estimates ice and snow ablation amount by combining a degree-day factor method, and calculates total glacier runoff; a single-layer evaporation model is constructed, net radiation, sensible heat, latent heat and water body heat storage and other fluxes are calculated based on a lake surface energy balance equation, and daily lake surface evaporation is obtained; quantile mapping and Bayesian fusion are combined to correct lake surface precipitation; non-glacier runoff is calculated according to a lake water balance equation; the stable period and the expansion period are divided according to the lake area trend, the stable period hydrological mean value is taken as a benchmark to calculate the expansion period abnormal value, and finally, the expansion contribution of each hydrological factor is determined according to the proportion of the abnormal value in the total water quantity increment. Through the method, the contribution intensity of different driving factors is clear, scientific support is provided for simulating lake change and predicting evolution, and ecological protection and management strategies are more targeted.

The application discloses a MRI paravertebral muscle segmentation method based on Bayesian fusion and probability shape modeling, and comprises the following steps: a) a Fourier-Gaussian process probability shape model is established to parameterize the muscle shape, the Fourier-Gaussian process probability shape model comprises radial modeling based on a Fourier basis function to represent a muscle cross-section profile, and axial modeling based on a Gaussian process to capture the axial variation law of the muscle shape; b) a muscle edge feature model based on a convolutional neural network is constructed to perform multi-scale feature extraction on the muscle edge in the MRI image; and c) a Bayesian segmentation framework is designed, and based on a maximum posterior estimation principle, online segmentation of the paravertebral muscle in the MRI image is realized. The application is customized according to the characteristics of the paravertebral muscle segmentation task through the idea of fusing high-quality artificial labeling and a powerful learning model, so that the application can achieve high segmentation and reconstruction quality under a small amount of interaction, and has strong shape change description capability.

The invention discloses a lightning stroke positioning method and system, relates to the technical field of power system safety protection, and solves the problem of large lightning stroke positioning error in a general scheme. An initial lightning stroke positioning clue is provided through electromagnetic wave data, the Joule heating effect of a discharge point is captured through infrared thermal imaging, non-lightning stroke condition interference is eliminated through a vibration spectrum, and under three-mode physical quantity complementation, multi-dimensional characteristics such as electromagnetic radiation, energy release and mechanical shock when the power transmission line is struck by lightning can be represented; bayesian fusion probability calculation is carried out based on the characteristics, so that more accurate lightning stroke points can be obtained, and protection starting and first-aid repair of a subsequent power system are facilitated.

The application discloses a bidirectional information retrieval enhancement generation method for a large language model, and belongs to the technical field of artificial intelligence. In order to overcome the defects of traditional RAG that only performs one-way retrieval from 'query to document' and introduces noise and omits key evidence, a bidirectional semantic perception retrieval enhancement generation model and a two-stage training framework are constructed. In the first stage, the positive / negative example distance is pulled apart in the embedding space in a contrast learning self-supervised manner. In the second stage, a supervised two-classification is used to finely distinguish the relevance of the query-document bidirectional sentence pair, and an output probability correlation is obtained. In the reasoning stage, the bidirectional probability is fused according to Bayes to obtain the final correlation degree, and the document is reordered. The whole process can realize plug and play without fine-tuning the LLM. The application significantly improves the accuracy and consistency of single-hop, multi-hop question answering and fact checking tasks, and has the advantages of light weight and low deployment cost.

This invention provides a method and system for constructing a negative obstacle risk map, relating to the field of robot environmental perception technology. The method includes: acquiring multimodal sensing data of a legged robot in the current operating environment to obtain the types of negative obstacles, multiple candidate regions, and the corresponding confidence and uncertainty of each candidate region; using a risk diffusion algorithm, performing ink blurring processing based on the type, confidence, and uncertainty to generate a continuous risk field corresponding to each candidate region; dividing the continuous risk field to generate a continuous risk gradient distribution corresponding to each candidate region; performing terrain modeling based on laser point clouds, updating the continuous risk gradient distribution using Bayesian fusion to obtain a multi-level grid map, and then performing tactile closed-loop correction on the multi-level grid map to generate a risk cost map. This invention improves the accuracy of constructing a negative obstacle risk map.

The invention relates to an infant asthma three-branch classification auxiliary judgment method and a medium, and relates to the technical field of data processing. The method comprises the following steps: collecting and preprocessing tidal respiration data and demographic data of infants, and performing heterogeneous feature extraction and grouping log-likelihood ratio acquisition on the preprocessed tidal respiration data and demographic data to obtain a log-likelihood ratio corresponding to each group; and performing hierarchical Bayesian fusion on each log-likelihood ratio to obtain a fusion result, and performing asthma risk auxiliary judgment of three-branch classification based on the fusion result. Compared with the prior art, the method can assist in judging the infant asthma more objectively and accurately based on the tidal respiration data.