285 results about "Metallogeny" patented technology

The invention discloses a mineral resource intelligent prediction method and system based on multi-source heterogeneous data fusion and deep learning, and the method comprises the steps: collecting and preprocessing multi-source heterogeneous data, and carrying out the standardization processing to form a structured data set; multi-source heterogeneous data fusion: realizing data layer space registration and feature layer weight dynamic allocation through an attention mechanism multi-modal fusion module, and outputting a high-dimensional metallogenic feature vector; constructing a CNN-LSTM mixed deep learning model and completing initialization training, and outputting an initial mineralization probability graph; and establishing a dynamic updating engine, performing model increment training based on transfer learning, correcting the mineralization probability through positive and negative sample reinforcement learning in combination with a newly added data type, and outputting a time sequence dynamic mineralization probability graph. According to the method, mineralization probability dynamic evaluation and risk quantitative updating are realized, the prediction precision and the model updating efficiency are improved, the method is adaptive to a multi-stage exploration scene, and accurate real-time support is provided for exploration decision making.

The embodiment of the invention provides a mineral target area intelligent delineation method and system based on multi-source heterogeneous geoscience data, and relates to the technical field of mineral resource exploration, and the method comprises the steps: dividing a multi-source heterogeneous geoscience data set comprising geological structure, geochemistry, geophysics and remote sensing image data into a plurality of data modules according to a geological action influence range; each data module records spatial distribution and attribute information, then a dynamic mapping relation between the data modules and a mineral product mineralization mechanism is constructed, a mineralization association chain between the data modules is generated based on the dynamic mapping relation, a cooperative change rule of nodes and connection paths is defined, then a target region feature set conforming to the mineralization association chain is screened, and a target region feature set is obtained; and finally, according to a collaborative change rule, judging the integrating degree of a target region feature set space unit and a mineralization condition, dynamically adjusting a space boundary range, and generating a mineral target region delineation result, thereby comprehensively utilizing multi-source data, deeply mining a relationship with a mineralization mechanism, and improving the accuracy and reliability of mineral target region delineation.

The invention relates to the technical field of mineral resource exploration. The prospecting method, device and equipment based on the multi-source geological relation data and the medium are provided, the method comprises the steps that space-time alignment and standardization processing are conducted on obtained geological historical evolution data, geophysical field data, geochemical migration data and remote sensing alteration information, and a dynamic knowledge graph is generated; performing mineralization stage division processing on the geological historical evolution data to obtain a mineralization stage division result; integrating the fluid migration space-time path network, performing three-dimensional dynamic modeling processing, and generating a staged three-dimensional metallogenic evolution model; extracting a stage-specific geological mark combination from the staged three-dimensional metallogenic evolution model, performing knowledge reasoning processing based on a preset historical ore deposit rule base, and outputting an ore prospecting target region and a metallogenic process constraint basis which meet a preset confidence coefficient condition, so as to improve the precision of a structural model, generate a staged fluid dynamic field, and improve the precision of the metallogenic process. And the target region prediction confidence is enhanced.

The invention discloses a method for constructing a large mineralization potential evaluation model based on LLM, and relates to the field of models.The method for constructing the large mineralization potential evaluation model based on LLM comprises the following steps that 1, a mineral geological map file is converted into a structured JSON format data set; step 2, constructing cue words, wherein the cue words at least comprise geological information extraction cue words, function task cue words and entity, relation and attribute extraction cue words; compared with the prior art, the method has the beneficial effects that the large mineralization potential evaluation model constructed by the method realizes text and map multi-mode mineral product geological map information identification and analysis, automatic mineralization geological feature analysis, mineralization feature information extraction and mineralization potential evaluation; the problems that in the prior art, man-made subjective influence exists, professional knowledge dependence is high, the geological information recognition accuracy rate in the recognition process is low, and information is lost during knowledge retrieval are solved.

The invention relates to the technical field of big data analysis, and discloses a prospecting target area positioning method and system based on big data, and the method comprises the steps: collecting multi-source exploration data in real time through distributed nodes, completing coordinate normalization, semantic alignment and time synchronization through a spatial heterogeneous data flow engine, and generating a standardized incremental data block; performing local feature sensitivity analysis based on the historical model library, identifying a newly added feature dimension, and performing parameter increment updating by adopting a sliding window gradient descent method; inputting the updated model into a target evolution model driven by a Bayesian space-time probability field, and dynamically calculating the metallogenic probability of each space grid in combination with a stress field, an element migration path and historical verification data; and generating high, medium and low three-level target area maps according to probability sorting, and pushing the high, medium and low three-level target area maps to a three-dimensional visual decision terminal. According to the method, minute-level dynamic response of the target region under triggering of newly-added data is realized, computing resource consumption is reduced to be less than 5% of that of an original system, and prospecting efficiency and abnormal region identification timeliness are improved.

The invention discloses a geological mineralization causal knowledge extraction method, a storage medium, equipment and a product, and relates to the field of geological mineralization, and the method comprises the steps: constructing a causal hypothesis of a causal role from an unstructured geological text; constructing a causal data set based on causal hypothesis, and training the natural language inference model by using the causal data set; wherein the input vector of the causal data set and the vector of the causal role are fused to form the input vector of the model; a bias matrix of a causal role is introduced to calculate a self-attention weight; obtaining gating weights of the causal role and the global context based on [CLS] embedding, and performing weighted summation on embedding of the causal role and [CLS] embedding by using the gating weights to obtain a final fusion representation; and identifying a high-confidence causal chain from the geological text by using the trained model to obtain a typical causal mode related to the specific mineralization. According to the invention, the chain type identification of the complex mineralization mode can be realized.

The invention discloses a gold mine resource potential prediction method fusing a geological knowledge graph and a large model, and belongs to the technical field of mineral resource prediction, and the method comprises the steps: aggregating geological exploration data streams, constructing a space-time event knowledge graph, driving a pre-trained large model to carry out continuous tensor projection, and carrying out prediction. Encoding the metallogenic mechanism into a gauge tensor to construct a geological semantic Riemannian manifold; constructing a neural differential equation set representing metallogenic dynamics on the manifold; by taking observation data as a boundary, calculating an energy dissipation minimum value path through variational solution and geodesic line optimization; locking and representing a negentropy flow accumulation area of the ore body through phase-space reconstruction and persistence coherence test; and holographic mapping is carried out on the accumulation area to form a materialized prospecting target area, and a dynamic causal transcription report is generated. According to the method, a generative dynamic inversion normal form based on a physical mechanism is adopted, metallogenic prediction is reconstructed into solving of an evolution problem of a differential equation in a manifold space, the space-time inevitability of a metallogenic system can be replayed from static observation data, and a prospecting target region with causal interpretation is generated.

The invention discloses an experimental device and method for controlling migration and mineralization of ore-forming fluid in a wrinkle deformation process, and belongs to the technical field of ore deposit geology. The device comprises an ore liquid synthesis unit and a mechanical deformation simulation and mineralization analysis unit. The mechanical deformation simulation unit comprises a box body, an extrusion deformation system, a liquid injection system and a heating temperature control system, and can synchronously realize visual analysis of structure extrusion, fluid injection and mineralization precipitation at high temperature. The experimental method comprises the following steps: firstly, preparing a simulated metallogenic fluid containing FeS2 (pyrite); laying simulated surrounding rock and wrinkles in the box body, arranging a separation layer, and heating; extruding the sand layer and injecting fluid to simulate a mineralization process; and slicing, sampling and analyzing after model consolidation, and establishing a mineralization space distribution model. The device is simple in structure and convenient to operate, the whole process of fold extrusion, crack extension, fluid migration and mineral precipitation can be repeatedly represented, and an experimental basis is provided for hydrothermal deposit mineralization mechanism research and prospecting prediction.

The invention relates to the technical field of big data processing, and discloses a data extraction method and system for geological mineral exploration, and the method comprises the steps: carrying out the standardization preprocessing of original data containing space coordinates, lithology texts, mineral components, logging curves and mineralization labels; spatial, semantic, concentration and time sequence deep representations are extracted in parallel through a multi-modal geologic feature encoder and fused into high-dimensional vectors; applying structured sparse constraint to the features by using a graph attention mechanism guided by an expert knowledge graph, and strengthening a mineralization association dimension; a dynamic incremental learning engine is combined with an elastic weight solidification mechanism to realize local fine tuning of model parameters and historical knowledge retention; and finally outputting a mineralization potential score, a mineralization factor sequence and an abnormal element combination. According to the method, through triple mechanisms of multi-modal fusion, knowledge embedding and incremental evolution, the accuracy, interpretability and timeliness of data extraction are improved, and the real-time analysis requirement of large-scale mineral exploration is met.

The invention discloses a mineral resource metallogenic law simulation and target prediction system based on big data, and relates to the technical field of geological exploration. The multi-source data acquisition and standardization module supports acquisition of five types of data, and the data are preprocessed and then transmitted to the distributed database; mining key elements by using an improved Apriori algorithm, and constructing a correlation graph; building a model based on Unity 3D, and integrating three types of dynamic simulation; performing three-level prediction by using a CNN-LSTM model; three-dimensional rendering and multifunctional display are supported; and automatically updating data, models and rules to form an optimized closed loop. According to the method, multi-source data is integrated to improve ore-forming element recognition comprehensiveness, dynamic simulation fits geological reality, AI prediction is accurate, uncertainty analysis is included, visual interaction is practical, iterative optimization continuously improves efficiency, invalid exploration cost is reduced, and mineral exploration is efficiently guided.

The invention relates to the technical field of mineral exploration, and discloses a method for estimating the mineralization probability of residual slope product type anatase based on multi-source parameters, and the method comprises the steps: determining a geographic region, collecting geological data, sampling a geological sample, and collecting the characteristics of the sample; extracting the first characteristic index set to judge the region classification of the geographic region, wherein the region classification comprises a conventional exploration region, a main mineralization mode region and a secondary mineralization mode region; extracting a second characteristic index set from the geological data to calculate a standard mineralization probability; calculating a weathering correction coefficient and a maturity correction coefficient; and correcting the standard mineralization probability to generate a mineralization probability, and judging whether the geographic region is a high-potential target region or not according to the mineralization probability. According to the technical scheme, the metallogenic probability judgment standard can be determined and corrected under different conditions, and judgment of a high-potential target region is achieved.

The invention discloses a tungsten deposit deep edge metallogenic prediction method based on machine learning, and particularly relates to the technical field of geological prediction and data processing. The method comprises the following steps: acquiring multi-source geological data, constructing a multi-dimensional space grid, and dividing candidate prediction units; quartz vein density, alteration indexes, geochemical combination anomaly weights and high-frequency magnetic anomaly waveform features are extracted, and an ore control feature tensor matrix is constructed; extracting a spatial dependency relationship among the candidate units based on a graph neural network, constructing a metallogenic potential prediction model, and outputting a metallogenic probability graph and a metallogenic hot spot graph; model parameters and feature weights are dynamically optimized through spatial superposition analysis and an abnormal response recognition mechanism; according to the method, the precision and efficiency of deep edge tungsten ore prospecting can be remarkably improved, and good self-adaptability and popularization and application value are achieved.

The invention belongs to the technical field of vanadium enrichment mechanisms of phosphorus vanadium ores, and discloses a research method of a vanadium enrichment mechanism in a diagenetic stage of phosphorus vanadium ores, which comprises the following steps: S1, sample collection and treatment; s2, rock ore identification and mineral composition analysis; s3, analyzing the occurrence state and microcell morphology of vanadium; s4, performing geochemical analysis on the whole rock; s5, in-situ microcell geochemical analysis is carried out; s6, phosphorus nodule analysis; s7, comprehensive analysis and mineralization model establishment; according to the method, mineralogy, total rock geochemistry, micro-area surface scanning and other multi-scale and multi-means research methods are comprehensively utilized, and the vanadium occurrence state, the ore-forming fluid evolution and the phosphorus-vanadium coupling relation are finely described; in-situ microcell geochemical analysis is introduced into phosphorus nodule analysis, the internal structure, the growth sequence and element distribution of the phosphorus nodule are directly revealed, obvious frontier and systematicness are achieved, and reliable theoretical support is provided for accurate exploration of vanadium ore resources and green and efficient dressing and smelting process research and development.

The invention relates to the crossing field of mineralogy and geochemistry, in particular to a mineral and element relation analysis method for gold-bearing minerals based on image matching and data fusion and application of the mineral and element relation analysis method. Comprising the steps of ore sample processing, gold-bearing mineral image calibration through AMICS, trace element scanning through fixed-point EPMA and EDS, image-level matching and spatial data fusion and gold-bearing mineral-element relation analysis. According to the method, the AMICS mineral map and the EPMA element information are fused, relation analysis of trace elements in the gold ore and visual reconstruction of a mineral-element corresponding mechanism can be achieved, and effective data and image models are provided for microcosmic metallogenic information requirements in digital mine construction.

The invention discloses a deep niobium phosphate ore positioning physical and chemical exploration method based on multi-method cooperation, and belongs to the technical field of geological mineral exploration. According to the method, a three-stage exploration system of region optimization, target region delineation and fine verification is constructed, multi-parameter cooperation of a magnetic method, an electromagnetic method, an induced polarization method, a three-component magnetic logging method and a geochemical method is combined, and each step is constrained by a basic rock-niobium phosphorite metallogenic model. An ore prospecting mark is determined through regional geological background analysis and metallogenic model construction, a metallogenic prospective region is delineated through regional optimization, a specific target region is delineated and locked, engineering verification is carried out through fine verification, and finally, a result is integrated to estimate the resource quantity. According to the method, the multiplicity of solutions of a single method is effectively reduced, the positioning precision of the deep niobium phosphorite is improved, the exploration efficiency and the target area ore finding rate are improved, and the method is suitable for accurate exploration of the deep niobium phosphorite.

The invention belongs to the technical field of sandstone-type uranium deposit mineralization prediction, and particularly relates to a sandstone-type uranium deposit comprehensive prediction method based on big data, which comprises the following steps: step 1, collecting and sorting data, and constructing a multivariate information database; 2, analyzing metallogenic characteristics and constructing a sample set; 3, developing and training a prediction model; and 4, packaging and applying the model. According to the method disclosed by the invention, the deep coupling of geological expert knowledge and a machine learning algorithm is realized through a full technical process of systematically integrating multi-source data fusion, multi-dimensional feature space construction, hybrid drive modeling and prediction function realization, so that the generalization ability of a sandstone type uranium mine prediction model is remarkably improved; the prediction normal form transformation from experience to quantitative decision making is realized, and a reproducible and verifiable technical solution is provided for optimization of the favorable metallogenic area of the sandstone type uranium deposit.

The invention discloses a mineralization potential evaluation and target region optimization method and system based on machine learning, and relates to the technical field of mineral resource exploration. The method comprises the following steps: acquiring multi-dimensional data of a target area; preprocessing the multi-dimensional data to obtain preprocessed key data; a metallogenic system conceptual model is constructed, and a hydrothermal migration path and a metallogenic fluid pressure field of the key data are calculated through finite element simulation for visual display; generating an evidence layer based on the key data to obtain multi-dimensional evidence layer data; and constructing a mineralization potential evaluation model, and inputting the multi-dimensional evidence layer data into the mineralization potential evaluation model for prediction to obtain a mineralization probability prediction result. Through multi-source data fusion and machine learning algorithm innovation, intelligentization and precision of mineralization potential evaluation and target region optimization are realized, and an efficient technical means is provided for mineral resource exploration.

The invention provides an intelligent prospecting method and device, electronic equipment and a storage medium. The problem that a satellite-borne platform or an airborne platform is not high in prospecting precision is effectively solved. The method comprises the steps of performing continuous imaging on a target to-be-measured mining area to obtain multi-frame remote sensing data, and preprocessing the multi-frame remote sensing data to obtain a target hyperspectral image sequence; selecting a reference frame and a to-be-registered sequence frame for registration, and superposing all registered images to intercept a public overlapping region image; carrying out collaborative quality enhancement reconstruction on the public overlapping region image to obtain a hyperspectral image, and respectively carrying out altered mineral and structural element identification on the hyperspectral image to obtain a mineral distribution map and a classification structural map; and fusing the mineral distribution map, the classification structure map and a preset geological metallogenic rule to obtain a prospecting distant view map with a prospecting mark, so as to complete intelligent prospecting of the target to-be-detected mining area based on the prospecting distant view map.

The invention relates to the technical field of mineral resource exploration, in particular to a deep concealed ore body prediction method and system. The method comprises the following steps: acquiring geological exploration data, geophysical data and lithologic physical property probability distribution data of a target area; constructing a three-dimensional geological model according to the geological exploration data; performing inversion calculation on the geophysical data by taking the three-dimensional geologic model and the lithologic physical property probability distribution data as constraints to obtain a three-dimensional geophysical model; fusing the three-dimensional geologic model and the three-dimensional geophysical model to obtain a three-dimensional geologic-geophysical model; and determining the mineralization probability of the deep concealed ore body according to the three-dimensional geology-geophysical model. The problem that in the prior art, deep hidden ore body prediction is not accurate enough is solved, the three-dimensional geology-geophysical model is gradually constructed by obtaining the geological exploration data, the geophysical data and the lithologic physical property probability distribution data of the target area to be explored, then ore body prediction is conducted, and the accuracy of ore body prediction is improved.

The invention provides a sandstone-type uranium deposit sedimentary facies identification method, system and device and a medium, and belongs to the technical field of sedimentary facies identification, and the method comprises the steps: obtaining sandstone-type uranium deposit sedimentary facies multi-source data; time-frequency domain feature data, texture feature and waveform feature data and element ratio feature and statistical feature data related to sedimentary facies in the sedimentary facies multi-source data are extracted; time sequence features, three-dimensional structure features and metallogenic environment features are extracted from the feature data and weighted fusion is carried out to obtain the sedimentary facies category recognition probability. Multi-dimensional information complementation is realized by combining logging, earthquake and geochemical data, covering vertical lithology change, three-dimensional sand body distribution and a sedimentary facies state in a redox environment scene, and the focusing capability and the recognition precision of the model are effectively improved.

The invention discloses a metallogenic prediction method and device based on fluid parameters and fluid field modeling, a medium and a product, and relates to the field of metallogenic prediction. The method comprises the following steps: firstly, carrying out lithofacies research on a fluid inclusion sample in a target area to determine a metallogenic stage; analyzing and testing the fluid inclusion samples at different mineralization stages to obtain a plurality of fluid parameters; exploratory data analysis is conducted on the multiple fluid parameters, and key fluid parameters closely related to the content of the main metallogenic elements are screened out; modeling the numerical relationship between the key fluid parameters and the main metallogenic elements by adopting a machine learning or deep learning algorithm, and determining an optimal numerical model; processing the key fluid parameters by adopting different spatial interpolation algorithms, and establishing a three-dimensional fluid field model; according to the three-dimensional fluid field model and the optimal numerical model, three-dimensional metallogenic prediction is carried out in combination with the metallogenic geological elements, and a prospecting target area is determined; the fluid parameters are introduced as predictive variables, so that the precision of metallogenic prediction is improved.

The invention discloses a rare metal mineralization potential comprehensive evaluation method based on rock geochemistry, and aims to solve the problems of single evaluation index and disjunction between field observation and indoor analysis in the prior art. The method comprises the following steps: obtaining geological data of an analysis area, and screening a target area based on a favorable structure background and an exposed feature criterion; identifying mineralogical and lithofacies markers and collecting sampling data; the method comprises the following steps: acquiring rock geochemical data of a sample sampled by a previous person, including multi-dimensional data including major elements, trace elements, isotope composition and the like, and calculating a quantitative evaluation index according to the data; and finally, establishing a comprehensive evaluation model by adopting a weighted scoring method to realize mineralization potential grade division and target region accurate delineation in a three-dimensional space. According to the method, organic combination of macroscopic geologic features and microcosmic geochemical data is realized, and a complete technical system from field observation to indoor analysis to engineering decision is formed.

The invention discloses a prospecting exploration method for ion adsorption type heavy rare earth ore in middle and low mountainous areas, and belongs to the technical field of geological mineral exploration. According to Y, Dy and Nb abnormity and Y-Nb combination abnormity areas such as water chemical exploration and soil chemical exploration of a working area, high-silicon, potassium-rich, alkali-rich and sphene-rich heavy rare earth secondary mineral mineralization mother rocks are preferably selected, and a favorable mineralization area of the ion adsorption type heavy rare earth ore is delineated by combining characteristic parameters that Y / Ce is greater than 0.9 and Dy / Ce is greater than 0.2; screening south and east-south-east abrupt slope (gradient of about 30 degrees) areas by utilizing a GIS spatial analysis technology, overlapping favorable mineralization areas of the ion adsorption type heavy rare earth ore, and comparing and determining an ion adsorption type heavy rare earth ore prospecting target area in a working area; whether mineralization abnormity exists in the heavy rare earth ore prospecting target area or not is verified by using a manual impact sampling drill and a rare earth ion leaching-titration qualitative analysis method; chemical samples are preliminarily collected, 15 components of ion phases are analyzed, whether heavy rare earth ore bodies exist or not is judged and evaluated, the prospecting exploration range of the ion adsorption type heavy rare earth ore is determined, and the prospecting efficiency of the ion adsorption type heavy rare earth ore is improved. According to the method, the mineralization prospective area of the ion adsorption type heavy rare earth ore can be rapidly delineated in a large range, the prospecting target area is narrowed, and the prospecting efficiency of the ion adsorption type heavy rare earth ore is improved.

The invention relates to the technical field of iron ore detection, and discloses a deep coverage area skarn type iron-rich ore target detection method based on gravity and magnetic data. The method comprises the steps of collecting and preprocessing gravity and magnetic measurement data of a target area to obtain a standardized gravity and magnetic data set; based on the geological background of the analysis area, the structure and lithology distribution characteristics are extracted, and the metallogenic conditions are matched to screen the potential metallogenic target area. And performing multi-scale decomposition on the gravity and magnetic data of the target region, obtaining different depth level abnormal features, constructing a three-dimensional geologic structure model, and obtaining density and magnetic susceptibility distribution based on model inversion. Accordingly, the ore body is recognized, spatial distribution features are extracted, continuity and scale of the ore body are determined through spatial correlation analysis, and a final prediction result is output after geological constraint condition optimization is combined. The method is suitable for a complex environment with signal shielding and abnormal superposition in a deep coverage area, deep ore body information can be accurately captured, and a feasible path is provided for skarn type rich iron ore detection.

The invention provides a nickel ore target region prediction method and system based on hyperspectral remote sensing data analysis, and relates to the technical field of mineral resource exploration, and the method comprises the steps: firstly obtaining a hyperspectral remote sensing data body of a to-be-predicted region, then carrying out alteration feature space clustering construction processing on the hyperspectral remote sensing data body, forming an alteration feature space cluster body, and carrying out the clustering construction processing on the alteration feature space cluster body; the method comprises the following steps: identifying spatial distribution of various geological alteration types and binding spectral features, then carrying out mineralization alteration combination sequential spatial evolution processing to obtain a mineralization alteration sequential evolution body, then carrying out target area indication feature anchoring shaping construction processing on the mineralization alteration sequential evolution body to form a target area indication space shaping body, and carrying out target area indication feature anchoring shaping construction processing on the target area indication space shaping body. And positioning key indication characteristics of the nickel ore target region, and finally carrying out nickel ore target region space consolidation delineation treatment to generate a nickel ore target region prediction result. According to the method, spectrum and space information of hyperspectral remote sensing data is fully utilized, and the accuracy and reliability of nickel ore target region prediction are effectively improved.

The invention discloses a new-type barite deposit mineralization mode construction method based on a same sedimentary fault. The method belongs to the field of geological exploration and mineral resource prediction, and comprises the following steps: analyzing the earth crust cracking activity history of an earthquake-Hangjian broken basin, and recovering a basin'checkerboard 'structure prototype; by means of field geological survey and research, drilling engineering, geophysics, remote sensing geological big data and the like, north-east-east-direction and north-west-direction co-sedimentary fault networks are identified and modeled, and a deep metallogenic fluid rising and jet flow channel is determined; the metallogenic process is concluded into a hydrothermal jet flow stage and an underwater gravity flow deposition stage, deep fluid is revealed to rise, jet flow and precipitate along a fault, and an ore-rich zone of a composite seabed fan body group is formed; and a geochemical prospecting prediction model combining trace element and sulfur isotope characteristics is established. The method systematically clarifies a coupling mechanism of ore control of the same sedimentary fault, ore-forming fluid migration and gravity flow deposition, and provides a theoretical basis and a technical means for prospecting prediction of the barite deposit in the Hendan-Hangjian fault basin.

The invention is suitable for the technical field of multi-modal data fusion, and provides a multi-modal data fusion deep learning geological map intelligent prediction method, which comprises the following steps: acquiring multi-modal geological data, constructing a heterogeneous multi-modal feature extraction network, and respectively extracting high-dimensional feature representation of each modal data by adopting a special encoder; designing a multi-modal dynamic fusion module based on a multi-head attention mechanism; establishing a deep learning architecture of a geological knowledge guiding mechanism, and embedding geological rules and priori knowledge into a model training process through a constraint loss function; implementing a multi-task collaborative learning framework, and synchronously completing lithology classification, structure identification and mineralization potential prediction tasks; outputting reliability evaluation of a prediction result by adopting an uncertainty quantification system of a Bayesian deep learning framework; deploying an intelligent active learning system; according to the multi-modal dynamic fusion method based on the multi-head attention mechanism, the problem of depth feature interaction and complementation among heterogeneous geological data is effectively solved.

The invention discloses a method for constructing a mapping knowledge domain of a metallogenic time-space event fused with a large model, which belongs to the technical field of computers and comprises the following steps of: acquiring multi-source heterogeneous geological data, generating a unified semantic primitive carrying a dynamic credibility weight through multi-modal semantic fusion, constructing a dynamic cognitive energy field based on a probability theory and a dynamics principle, and constructing a mapping knowledge domain of the dynamic cognitive energy field. Releasing a probability event probe in an energy field, generating an initial spatio-temporal event chain containing a plurality of possible paths through potential energy gradient descent and probability exploration, constructing a cognitive isomer system containing an expert simulator, a data insight body and a meta-cognitive arbiter, performing cognitive game on the initial event chain to obtain a game result, and performing cognitive game on the initial event chain. State prediction is carried out based on multi-dimensional health indexes, and predictive self-repairing is carried out on the knowledge graph; by adopting the technical scheme of constructing a dynamic cognitive energy field and a cognitive isomer system for coevolution, dynamic evolution, deep cognitive gaming and predictive self-repairing of the knowledge graph can be realized.

The invention relates to the technical field of deep learning, in particular to an intelligent prospecting model construction method based on a knowledge graph and data deep learning, which comprises the following steps: collecting multi-source geological data to perform time decomposition and spatial stratified sampling to extract features, calculating an attachment weight through semantic coding to construct a geological knowledge structure, and constructing a geological prospecting model; the method comprises the steps of extracting spatial-temporal features in a convolution mode, combining with semantic deviation degree weighted fusion to generate a hierarchical feature coupling result, carrying out aggregation analysis on spatial-temporal correlation to extract consistent components, judging a metallogenic response relation through conditional probability reasoning, fitting a model, calculating deviation, adjusting weights, analyzing semantic consistency, and carrying out classification and aggregation to generate an intelligent prospecting optimization result. The feature precision is improved through time decomposition and spatial stratified sampling of multi-source geological data, data association is enhanced through semantic coding, time-space consistency is enhanced through convolution extraction and semantic fusion, multi-scale features are balanced through hierarchical coupling, the ore-forming relation judgment accuracy is improved through probabilistic reasoning, and the result precision and stability are remarkably improved.

The invention provides a gold mine prospecting target area intelligent delineation method and system based on multi-source geological data, and relates to the technical field of mineral exploration. Remote sensing images, geophysical exploration and earth surface rock chemical data associated with gold mine mineralization are collected, and according to the gold mine mineralization characteristics, the gold mine prospecting target area intelligent delineation method and system based on the multi-source geological data are obtained; correcting gold element space distribution difference, decomposing mineral spectrum mixing information, and strengthening mineralization related characteristic information. Then mining a data feature association relationship based on the feature information, the physical exploration data and the geochemical data, constructing a metallogenic association network, and inputting the feature information to obtain metallogenic association parameters; calculating mineralization probability values point by point in combination with spatial distribution characteristics of the multi-source geological data, generating a continuous mineralization probability curved surface, finally screening areas with probability values higher than a preset threshold value, locking a conforming closed area in combination with a typical gold ore deposit model, and recording coordinate boundary information to generate a gold ore prospecting target area map. The intelligent and accurate delineation of the gold ore prospecting target area can be realized.