64 results about "Mineral identification" patented technology

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 a target mineral identification method and device and computer equipment. Comprising the following steps: firstly, primarily identifying concentrate of a main ore belt or a main ore spot, so that the concentrate containing target minerals can be effectively identified, the subsequent data processing pressure is reduced, and the primary detection efficiency and accuracy are improved; next, the pixels of the secondary ore zone are updated to weaken false ore position information caused by the edge and thickness of the ore, and mistakes and omissions of subsequent identification are avoided; and finally, the target ore plot after pixel updating is accurately re-identified based on the main ore plot, so that the overall performance of ore detection is improved.

This invention discloses a Monte Carlo-based mineral assemblage analysis method, belonging to the field of mineral analysis. The invention includes the following steps: multi-source data fusion and preprocessing; physical model construction and initial solution generation; multi-scale feature fusion and extraction; Monte Carlo random sampling and solution space exploration; physical-data dual-driven evaluation and screening; iterative update and model optimization; convergence judgment and result output. This invention effectively solves the problem of multiple solutions in mineral assemblage identification by combining multi-source data fusion, a physical-data dual-driven model, and the Monte Carlo method with multi-scale feature fusion and iterative optimization. This method can integrate geophysical, geochemical, remote sensing, borehole core, and mineral spectral data, and through iterative model updates, gradually converges to the most probable mineral assemblage, providing uncertainty assessment, thereby improving the accuracy and reliability of mineral identification.

The invention discloses a heavy mineral placer prediction method, device and equipment based on paleo-coastline reconstruction, and the method comprises the steps: determining the paleo-sea level relative height of a sample region, and generating a target paleo-coastline through a region growing algorithm; generating an ancient landform elevation model, identifying a plurality of ancient landform units based on the topographic position index, and screening out ancient landform exposure units; performing mineral identification on the ancient landform exposure unit to obtain a heavy mineral abundance map; constructing a hydrodynamic-deposition coupling model, identifying a sediment accumulation area of the sample area, and comparing the sediment accumulation area with the heavy mineral abundance map to obtain a heavy mineral enrichment area; dividing a positive sample area and a negative sample area, and training to obtain a heavy mineral placer prediction model; a mineralization probability distribution diagram of the target area is obtained through prediction, and the heavy mineral target area is determined according to the mineralization probability distribution diagram. The method improves the prediction precision of the mineralization probability of the heavy minerals, thereby improving the efficiency and accuracy of positioning and exploration of heavy mineral placers, and can be applied to the technical field of resource detection.

The application discloses a mineral identification method based on Monte Carlo simulation, comprising the following steps: S100, placing a prepared sample on a sample stage of a scanning electron microscope, controlling the sample stage to move, and splicing out a light microscope image or a BSE image; S200, selecting a target area in the spliced light microscope image or BSE image; S300, causing the scanning electron microscope and the energy spectrometer to scan the target area, and obtaining a mineral distribution map of the sample; wherein the EDS parameters corresponding to the energy spectrometer include a scanning step distance, and the scanning step distance is determined in the following manner: adopting a Monte Carlo simulation method, determining the horizontal width of the element characteristic X-ray of the mineral in the sample; and according to the horizontal width of the characteristic X-ray, determining the scanning step distance. Through the constitution, the identification accuracy and efficiency of the complex mineral in the rock sample are effectively improved.

The invention relates to the technical field of mineral recognition, in particular to a mineral recognition method based on a neural network. The method comprises the following steps: dividing a target mineral video into a plurality of shot segments to obtain A; traversing A to obtain a visual feature vector Fi, v, a voice feature vector Fi, a and a text feature vector Fi, t of Ai; when i > = p + 1, a fusion feature Mi corresponding to Ai is obtained, Mi = [Fi, v, Fi, a, Fi, t, Fi, b, Oi-1, Oi-2,..., Oi-j,..., Oi-p], Fi and b are mineral clustering result features corresponding to Ai, and Oi-j is a content feature corresponding to the (i-j) th shot segment; inputting the Mi into a trained neural network model, and obtaining structured information corresponding to the Ai; the structured information corresponding to the Ai comprises the scene type of the current shot and the name and state of the appearing mineral product. According to the invention, the accuracy of mineral product identification is improved.

The invention discloses a mineral combination analysis method based on Monte Carlo, and relates to the field of mineral analysis, and the method comprises the following steps: multi-source data fusion and preprocessing; constructing a physical model and generating an initial solution; performing multi-scale feature fusion extraction; monte Carlo random sampling and solution space exploration are carried out; performing physical-data dual-drive evaluation and screening; carrying out iterative updating and model optimization; and carrying out convergence judgment and result output. Through multi-source data fusion, a physical-data dual-drive model and a Monte Carlo method, and in combination with multi-scale feature fusion and iterative optimization, the problem of multiplicity of solutions of mineral combination recognition is effectively solved. According to the method, geophysics, geochemistry, remote sensing, drilling core and mineral spectrum data can be integrated, the model is updated through iteration, the most possible mineral combination is gradually converged, uncertainty evaluation is provided, and therefore the accuracy and reliability of mineral recognition are improved.

The present application belongs to the technical field of oil and gas exploration, and particularly relates to a kind of exploration method of restricted tidal flat facies carbonate rock gas reservoir. Based on rock, logging data, seismic data, experimental test analysis data, through microfabric analysis, macro and micro combination approach, through rock fabric and mineral identification, restricted tidal flat facies rock development characteristics and regional scope are identified and defined; wherein the rock samples include pore development samples and samples with lithology of dark mudstone and argillaceous carbonate rock; frequency spectrum analysis method, weighted average method, organic matter mass balance method and coherent technology method are used to construct high-frequency sequence lithology-electricity interpretation model and multi-scale through-source fault transport pattern; thus, restricted tidal flat facies carbonate rock gas reservoir accumulation mode is obtained to explore restricted tidal flat facies carbonate rock gas reservoir. The present application innovatively explores restricted tidal flat facies carbonate rock gas reservoir, and solves the technical problems of identification and fine description of this type of gas reservoir.

The invention provides a mineral dynamic identification and accurate sampling method and system based on deep learning, and the method comprises the steps: obtaining mineral image data and laser radar ranging data on a mine car in an underground environment, and carrying out the preprocessing of the data, and obtaining mineral feature data; designing a deep convolutional neural network architecture with multi-scale feature fusion and performing multi-stage training to determine a mineral recognition model; performing target detection by using a mineral recognition model, and realizing multi-target tracking through a Kalman filter and a Hungary algorithm; calculating mine car motion parameters by using FAST corner detection, ORB descriptors and an optical flow algorithm; predicting the future position of the target mineral by using multi-sensor fusion and an extended Kalman filter; and based on the predicted position, precise sampling operation is executed through quintic polynomial interpolation and dynamic compensation control. According to the invention, high-precision mineral identification and dynamic accurate sampling can be realized in a complex underground environment, and the representativeness and production efficiency of mineral sampling are obviously improved.

The invention provides a mineral identification reliability-driven task-type hyperspectral quality evaluation method, which relates to the technical field of hyperspectral remote sensing, and comprises the following steps: initializing P evaluation task containers of P types of target evaluation minerals; executing spatial index segmentation on the hyperspectral data cube to obtain P spatial data subsets; performing mineral exclusive quality analysis process treatment in an isolated manner, and outputting P mineral reliability feature sets; calculating P mineral recognition reliability indexes; mapping and extracting P-pixel-level local signal-to-noise ratios and P-pixel-level absorption depth stability; executing reliability partitioning, and outputting P reliability hierarchical mapping results; and outputting a global mineral recognition reliability thermodynamic diagram. The technical problem that the subsequent mineral recognition result is unreliable due to the fact that a hyperspectral data quality evaluation method in the prior art focuses on evaluation by using global image quality indexes and cannot reflect key diagnosis wavebands on which specific mineral recognition depends is solved.

The invention discloses an intelligent recognition green separation method and system for pegmatite type lithium ores, and relates to the technical field of mineral recognition and separation. Training an intelligent identification and sorting decision model; ore pretreatment and intelligent roughing waste throwing; stage ore grinding and intelligent real-time separation; by means of the method, the high recovery rate of lithium minerals and high-grade concentrate output can be achieved.

The application relates to a U-Net shale authigenic mineral identification method based on a residual structure, and relates to the technical field of geophysics. The method comprises the following steps: acquiring sample backscattering, cathodeluminescence and element distribution image data; constructing a data set and making labels; inputting the data set into a U-Net neural network model based on a residual structure to perform training, so as to obtain a network model capable of identifying different types of authigenic minerals; and using the trained U-Net model to perform pixel-level fine segmentation on different types of authigenic minerals in a to-be-detected image, so as to realize high-precision automatic classification of different types of authigenic minerals. The method effectively solves the problems of great difficulty and low efficiency in identifying different types of authigenic minerals in fine-grained shale, and realizes the needs of rapid and accurate segmentation and quantitative analysis of a large number of samples, thereby providing important microscopic image basis for the research contents of shale oil and gas reservoir physical property changes and reservoir reconstruction schemes.

The embodiment of the application discloses a kind of based on image segmentation's paragenesis mineral identification method and system, the method and system include obtaining mineral image and marking and expanding mineral image segmentation data set, construct with Swin Transformer as encoder, improved feature pyramid as decoder mineral image segmentation model, and using multi-scale pyramid pooling and global attention module to fuse the mineral feature information of different scales, obtain more comprehensive and rich mineral feature representation, effectively integrate the context information of mineral image, strengthen the extraction ability of model for different abstract level features, maintain the richness of feature map, improve mineral segmentation performance, when training, using transfer learning to freeze the weight of the encoder Swin Transformer after pre-training in ImageNet and fine-tuning in mineral classification data set, the model obtained using mineral segmentation data set is trained, the obtained model solves the problem that existing method and system can only identify mineral species in paragenesis mineral image, cannot accurately locate various mineral.

The application discloses a mineral identification analysis method and system based on calculation of a polarized light field reconstruction, belongs to the technical field of geological mineral analysis and microscopic imaging, and solves the triple bottleneck problem of physical contradiction-algorithm fragmentation-experience dependence in the prior art. At least one group of original light field image sequences of a sample to be measured in multiple visual angles and multiple polarization states are acquired; registration processing is performed on the original light field sequence images, so that the images under all visual angles correspond in spatial positions, and registration data are obtained; a degradation relation model for describing the original light field image sequence and a target light field image is established; based on the degradation relation model and the registration data, a polarization synthesis image is generated through reverse solving; morphological texture features and optical physical features are extracted from the polarization synthesis image, and mineral types and distribution information are determined. The application realizes automation, quantification and intellectualization of mineral identification, and improves the accuracy and efficiency of analysis.

The invention discloses a carbonate rock cross-scale mechanical property characterization method. The carbonate rock cross-scale mechanical property characterization method comprises the following steps: S1, basic physical property characterization; s2, processing a carbonate rock micromechanics experiment sample; s3, scanning electron microscope observation and microcosmic mineral identification; s4, correcting the area function of the needle tip of the pressing needle; s5, testing the micromechanical property of the carbonate rock mineral; s6, carrying out data arrangement on the micro-mechanical properties and the composition proportion; and S7, constructing a mechanical upscaling model and calculating macromechanical properties. According to the method, main mineral types in carbonate rocks are identified by utilizing a scanning electron microscope and energy spectrum analysis on a microscopic scale, and then the mechanical properties of different minerals are quantitatively represented by utilizing quasi-static nanoindentations. On the basis, mineral composition proportion information and porosity data are synthesized, an upscaling model of the mechanical property is constructed, and cross-scale prediction and evaluation of the macroscopic mechanical property of the carbonate rock are achieved.

The invention discloses a remote sensing geological prospecting method based on information entropy-partial differential equation combined modeling, and belongs to the technical field of mineral exploration, and the method comprises the steps: extracting a plurality of layers from a remote sensing image, the plurality of layers including a spectral angle map layer, an iron stain alteration grading layer, a hydroxyl alteration grading layer and an indication mineral distribution layer; superposing the multiple layers to generate a comprehensive graph; establishing a target region extraction model, and outputting a target region by taking the comprehensive graph as input; and vectorizing the boundary of the target region, and delineating the position of the target region. According to the information entropy-partial differential equation combined modeling-based remote sensing geological prospecting method disclosed by the invention, visual innovation of mineral space distribution is realized, four mineral identification technologies are cooperatively applied, the mineral strength is quantified into a transparency parameter, the problem of information overload due to multi-layer superposition is solved, automatic and rapid mining area identification is realized, and the mining efficiency is improved. And the identification accuracy is extremely high.

The application discloses a remote sensing geological prospecting method based on information entropy-partial differential equation joint modeling, and belongs to the technical field of mineral exploration, and comprises the following steps: extracting multiple layers from remote sensing images, wherein the multiple layers comprise a spectral angle mapping layer, an iron staining alteration grading layer, a hydroxyl alteration grading layer and an indicator mineral distribution layer; superimposing the multiple layers to generate a comprehensive map; establishing a target area extraction model, taking the comprehensive map as input and outputting a target area; and vectorizing the target area boundary to delineate the target area position. The remote sensing geological prospecting method based on information entropy-partial differential equation joint modeling realizes mineral spatial distribution visualization innovation, cooperatively applies four mineral identification technologies, quantifies mineral intensity into a transparency parameter, solves the problem of information overload caused by multiple layer superimposition, realizes automatic and rapid identification of a mining area, and has extremely high identification accuracy.

The invention discloses a mineral identification method and system based on an infrared spectrum. The method comprises the following steps: acquiring a mineral spectrum of a to-be-identified sample; processing the mineral spectrum to obtain wavelengths, absorption depths and prominences of a plurality of absorption peaks of the sample to be identified; aiming at each absorption peak P of the sample to be identified, using wavelength as key input, querying in the standard mineral spectrum query tree to obtain a plurality of standard mineral absorption peaks in a preset value x range, and screening to obtain a standard mineral absorption peak RP closest to the query wavelength; according to the screened standard mineral absorption peak RP, obtaining all standard minerals possibly corresponding to the to-be-identified sample; if all the characteristic absorption peaks of a certain standard mineral correspond to each other in the to-be-identified sample, adding the standard mineral into a list of candidate minerals of the to-be-identified sample; and identifying the main mineral of the sample to be identified from the candidate mineral list. According to the invention, the expandability and reliability of the mineral identification method are greatly improved.

The invention relates to a molybdenite main mineral hyperspectral multi-feature fusion identification method and system, and belongs to the technical field of mineral identification and spectral analysis. By collecting multi-angle spectral data and extracting hyperspectral wave band characteristics, a ground object spectrum library is constructed, the defect that traditional single-angle spectral data is insufficient in characterization of anisotropic reflection characteristics of mineral crystals is effectively overcome, and completeness and distinction degree of spectral characteristics of molybdenite of different grades are remarkably improved; according to the constructed rapid recognition model, the Euclidean distance, the cosine similarity and the spectral data divergence are fused with the weighted score to serve as a curve similarity evaluation criterion, the weight can be adjusted in a self-adaptive mode, the problem that a traditional method depends on a single weight or a fixed index is solved, rapid recognition of minerals is achieved, and the recognition accuracy is improved.

The invention discloses an intelligent exploration system based on unmanned aerial vehicle multispectral remote sensing and AI mineral recognition, and relates to the technical field of geological exploration. A six-rotor folding platform is adopted, a magneto-rheological damping mounting and multi-load interface is matched, a differential RTK-GPS and a millimeter wave obstacle avoidance radar are integrated, a 20-waveband camera, a thermal infrared camera and a laser radar are included, waveband combination is dynamically adjusted, and multi-sensor data space-time alignment is achieved; the time series data preprocessing module executes three-stage correction, fuses time series data and filters noise; a multi-modal fusion framework is adopted, and a transfer learning library is built in; a three-dimensional model is constructed, and mining simulation and multi-dimensional analysis are supported; and real-time mapping, data transmission and intelligent task planning are realized. According to the invention, exploration efficiency and identification precision are improved, complex environment adaptability is enhanced, data security is guaranteed, ecological protection is considered, seamless connection of exploration and mining is realized, and cost is reduced.

The invention provides an electromagnetic prospecting device and method based on an automobile shell, and the device comprises at least two electromagnetic signal collectors which are used for collecting electromagnetic signals in at least two directions; the common-mode signal suppression module is used for eliminating common-mode signals caused by environments and vehicles in the electromagnetic signals and generating differential-mode signals caused by characterization minerals; the vehicle-mounted dynamic interference suppression module is used for collecting interference source noise signals of the vehicle and eliminating the interference source noise signals in the differential mode signals to obtain pure signals; the prospecting module is used for inputting the pure signal into a mineral identification model to obtain the mineral existence probability and the mineral type; the mineral identification model is a deep learning model for representing the mapping relation between the pure signal and the mineral existence probability and the mineral type. The automobile shell serves as the antenna, the prospecting efficiency is improved, and the prospecting accuracy is improved through the electromagnetic signal processing process.

The application belongs to the technical field of remote sensing application, and specifically discloses a copper-lead-zinc mineralization alteration information extraction method and system based on multispectral remote sensing. The method receives multispectral remote sensing image data and generates surface reflectivity data; the aforementioned data is processed based on a spectral feature library to identify target mineral combinations and quantitatively delineate spatial distribution of alteration zoning; vegetation coverage areas are eliminated and background interference is suppressed to generate an alteration intensity grading map; a visual map is generated based on the grading map; a comprehensive report is generated and suggestions for anomaly grade evaluation and ore prospecting target area delineation are proposed; multispectral remote sensing image data, surface reflectivity data and the alteration intensity grading map are archived; and an interface is used to realize interaction with a remote sensing platform and GIS software. The system comprises remote sensing data acquisition, spectral preprocessing, alteration mineral identification, information extraction, result output, data storage and management and system integration modules. The application has the characteristics of high efficiency and precision, clear extracted information and strong practicality.

The invention discloses a mineral identification analysis method and system based on polarization light field reconstruction calculation, belongs to the technical field of geological mineral analysis and microscopic imaging, and solves the three bottleneck problems of physical contradiction-algorithm splitting-experience dependence in the prior art. Obtaining at least one group of multi-view and multi-polarization original light field image sequence of the sample to be detected; registration processing is carried out on the original light field sequence image, so that the images at all visual angles correspond to one another in spatial positions, and registration data is obtained; establishing a model for expressing a degradation relationship between the original light field image sequence and the target light field image; based on the degradation relation model and the registration data, generating a polarization synthesis image through reverse solution; morphological texture features and optical physical features are extracted from the polarization synthesis image, and mineral types and distribution information are determined. According to the invention, automation, quantification and intelligence of mineral identification are realized, and the accuracy and efficiency of analysis are improved.

The invention provides a mining and metallurgy product intelligent identification method and system based on a dynamic knowledge base, and relates to the technical field of mining and metallurgy product customs supervision. Aiming at the problem of low mineral identification accuracy and efficiency in the prior art, the method comprises the following steps: acquiring mineral attribute information, classification standard rules, risk characteristics and multi-source public data, updating the multi-source public data in real time, and carrying out information association to form a multi-dimensional dynamic knowledge base; all-element spectral data and crystal structure diffraction data of the to-be-detected mining and metallurgy product are collected on site, and element information and phase information are obtained; performing multi-modal data fusion on the element information, the phase information and the mineral industrial grade or element abundance, and determining a final mineral type name; and according to the quality standard, the classification rule, the forbidden and limited list and the solid waste characteristics in the knowledge base, performing compliance checking, classification judgment and risk screening, and outputting a mineral identification result, a risk label and a compliance suggestion. And an efficient and accurate identification method is provided for customs on-site supervision scenes.

The application provides an image processing and rock mineral identification method based on high-frequency filtering and mineral component attention, and belongs to the technical field of rock mineral identification. The method is started from the perspective of the frequency domain, the discrete cosine transform is introduced into the CNN architecture, high-frequency features are explicitly enhanced, high-frequency information is directly extracted and enhanced, and the influence of the smoothing effect of the CNN in layer-by-layer transmission on the detail information can be effectively relieved; the multiple attention mechanisms in the channel dimension and the spatial dimension enable the model to automatically determine which features are more important according to the current input rock mineral image, and realize efficient adaptive optimization and extraction of complex texture structures. Experimental results show that the strategy of explicitly enhancing high frequencies in the frequency domain and the spatial-channel double attention collaborative work makes the model show higher identification accuracy when facing actual rock mineral images with complex composition, variable structure and strong background interference.

This application provides a method and system for intelligent identification of minerals in weak information areas based on transfer learning, relating to the field of transfer learning technology. First, a source domain mineral sample set and a set of mineral samples to be identified in weak information areas are obtained. Then, geological correlation elements between the two are extracted and a cross-domain feature mapping is constructed. The original features of the minerals in the weak information areas are subjected to transfer adaptation processing to generate intermediate features of the minerals in the weak information areas that are adapted to the feature dimensions of the source domain. Next, sparse feature dimensions in the intermediate features are identified, and the corresponding feature distribution patterns of the source domain are used to complete the features, generating completed features. The completed features are input into a pre-trained transfer learning identification model for cross-domain identification, generating preliminary identification results. Finally, source domain samples with similar geological correlation elements are selected to determine the transfer deviation, correct the preliminary identification results, and generate the final identification results, effectively improving the accuracy and reliability of mineral identification in weak information areas.

The application provides a silver mineral particle size determination method, and belongs to the technical field of process mineralogy. The method comprises the following steps: sample preparation, automatic mineralogical analysis, silver grade calibration, silver mineral identification and data analysis, and calculation of silver mineral particle size. During the automatic mineralogical analysis, the original particle size data obtained by measurement is adjusted according to the specific occurrence state of silver minerals in ores. During the silver mineral identification and data analysis, a correction coefficient K is introduced to correct the system deviation caused by factors such as uneven mineral composition, coarse silver particles, automatic mineral analysis identification threshold and the like, so that the subsequent particle size distribution calculation based on image analysis is established on a more reliable "quality basis". The application replaces a large amount of manual labor with automatic mineralogical analysis, reflects the real occurrence characteristics through the "process particle size" reorganization rule, corrects the system error through the chemical grade calibration, and finally obtains the particle size distribution data with high confidence.

The application provides a mineral identification reliability driven task type hyperspectral quality evaluation method, relates to the technical field of hyperspectral remote sensing, and comprises the following steps: initializing P target evaluation mineral evaluation task containers; performing spatial index segmentation on a hyperspectral data cube to obtain P spatial data subsets; performing mineral exclusive quality analysis process isolation to output P mineral reliability feature sets; calculating P mineral identification reliability indexes; mapping and extracting P pixel level local signal-to-noise ratios and P pixel level absorption depth stabilities; performing reliability partitioning to output P reliability grading mapping results; and outputting a global mineral identification reliability heat map. The application solves the technical problem in the prior art that the hyperspectral data quality evaluation method focuses on using global image quality indexes for evaluation and cannot reflect key diagnostic bands relied on by specific mineral identification, thereby leading to unreliable subsequent mineral identification results.

This application relates to a machine vision-based method for identifying mixed and incorrect materials on a conveyor belt and detecting over- and under-screen mineral particles. The method includes: acquiring target material information from a logistics transportation system; extracting multiple frames of monitoring images from monitoring videos of the mineral transportation site; correcting each mineral image to obtain a corrected image set; using a corresponding recognition method to identify the corrected image set and obtain the mineral identification result corresponding to the on-site image; and simultaneously sending the corrected image set to a particle size detection module based on the acquisition location to obtain accurate over- and under-screen particle size detection results. This solution employs a machine vision-based system for identifying mixed and incorrect materials on a conveyor belt and detecting over- and under-screen mineral particles. It can perform real-time analysis of the material types transported on the conveyor belt, promptly detect mixed and incorrect materials, and simultaneously detect the powder content and large particles in the material on the over- and under-screen belts of a vibrating screen, reducing production losses.

The embodiment of the invention provides a weak information area mineral intelligent identification method and system based on transfer learning, and relates to the technical field of transfer learning, and the method comprises the steps: firstly obtaining a source domain mineral sample set and a weak information area mineral to-be-identified sample set, then extracting geological correlation elements of the two, and constructing cross-domain feature mapping; carrying out migration adaptation processing on the original features of the minerals in the weak information area, generating intermediate features of the minerals in the weak information area adapted to the feature dimensions of the source domain, then identifying sparse feature dimensions in the intermediate features, calling the feature distribution rule of the corresponding dimension of the source domain for complementation, generating complemented features, and carrying out the migration adaptation processing on the original features of the minerals in the weak information area; the complementation features are input into a pre-trained transfer learning recognition model for cross-domain recognition, a preliminary recognition result is generated, finally, source domain samples of similar geological correlation elements are selected to determine transfer deviation, the preliminary recognition result is corrected, a final recognition result is generated, and the accuracy and reliability of mineral product recognition in the weak information area are effectively improved.