CN-121996979-A - Geological mineral exploration data processing method based on big data acquisition

CN121996979ACN 121996979 ACN121996979 ACN 121996979ACN-121996979-A

Abstract

The invention relates to the technical field of geological mineral exploration and big data analysis and processing, in particular to a geological mineral exploration data processing method based on big data acquisition; the method comprises the steps of synchronously and structurally extracting investigation decision-making and cognition assumption information during multi-source data acquisition, converting the investigation decision-making and cognition assumption information into phase behavior semantic vectors, embedding the phase behavior semantic vectors into data units to form a phase semantic constraint data set with cognition background perception capability, dynamically generating a trusted interval through calculating phase cognition consistency indexes, softening abnormal data weights, constructing an enhanced phase trusted data set, dynamically reconstructing a correlation network between data on the basis, enabling the correlation structure to be adaptively adjusted along with investigation cognition deepening, and finally generating a standardized target expression unit capable of directly supporting prospecting deployment and resource configuration through identifying stable data structures and self-adaptive granularity expression. The invention realizes the natural conversion from the original data to the decision support information.

Inventors

ZHANG YU
YANG HUA
LI XIAOLONG
ZHANG DEEN
ZHANG WEI
HUANG FEI
YUAN WEN
LUO XUE
LV GUOYING
Ru peng

Assignees

河南省地质研究院

Dates

Publication Date: 20260508
Application Date: 20260205

Claims (10)

1. The geological mineral exploration data processing method based on big data acquisition is characterized by comprising the following specific implementation steps: S1, synchronously extracting and structuring decision and cognitive hypothesis information expressing a current exploration stage in a multi-source exploration data acquisition process, converting the decision and cognitive hypothesis information into a stage behavior semantic vector and embedding the stage behavior semantic vector into a corresponding data unit to form a stage semantic constraint data set with cognitive background perception capability; S2, based on the staged semantic constraint data set, computing a stage cognition consistency index of data in a stage, dynamically generating a trusted interval, computing a trusted weight of each piece of data, and forming an enhanced stage trusted data set; S3, introducing a exploration stage cognitive evolution mechanism based on the enhanced stage trusted data set, dynamically reconstructing an association network between data, and performing self-adaptive sparsification processing on the association network to form an enhanced self-adaptive association data set; S4, identifying stable local structural units based on the enhanced self-adaptive associated data set, adaptively determining the expression granularity of each structural unit according to the demand of the prospecting task, generating corresponding multi-granularity characteristics, and finally integrating the expression granularity characteristics into a standardized prospecting target expression unit.
2. The geological mineral exploration data processing method based on big data acquisition according to claim 1, wherein in step S1, the multi-source exploration data comprises: remote sensing image data, geophysical survey data, geochemical sampling data and engineering geological record data which are synchronously collected in the same investigation stage; Recording a phase identifier, a spatial position attribute and a collection time attribute of the investigation phase to which each piece of data belongs for each piece of data; the phase behavior semantic vector is generated by extracting and structuring the investigation design description, the abnormal demarcation basis, the cause hypothesis direction and the verification priority information of the phase; The phase behavior semantic vector is embedded into single data of the same phase through a behavior semantic mapping function to form an extended data unit with interpretation constraint, and the extended data unit is clustered into a phase semantic constraint data set with clear cognitive boundary according to the exploration phase.
3. The geological mineral exploration data processing method based on big data acquisition according to claim 2, wherein in step S2, calculating a stage cognitive consistency index of data in a stage specifically includes: Extracting an original observation value set and embedded behavior semantic mapping of each piece of data in the staged semantic constraint data set, and acquiring a related data set in a space or a causal neighborhood of the data; And comprehensively calculating the consistency relation of the original observed value, the behavior semantic map and the neighborhood data of the data through the stage consistency evaluation function, and outputting a numerical index representing the cognitive matching degree of the data with the current stage.
4. A geological mineral exploration data processing method based on big data acquisition according to claim 3, wherein in step S2, dynamically generating a trusted interval specifically comprises: Counting the mean value and standard deviation of the stage cognition consistency indexes of all data in the current investigation stage; Based on the mean value and the standard deviation, and by utilizing the expansion or convergence degree of the adjustment coefficient control interval, the upper and lower boundaries of the credible interval of the credible degree range of the characterization data under the cognition of the stage are calculated.
5. The geological mineral exploration data processing method based on big data acquisition according to claim 4, wherein in step S2, the trusted weight calculation process specifically comprises: firstly, calculating the deviation degree of a stage cognition consistency index of each piece of data and the mean value of the stage consistency index; Then adopting an exponential decay function, and calculating the credible weight of each piece of data according to the deviation degree, so that the larger the deviation degree is, the lower the weight obtained by the data is, and the softening treatment of the abnormal data is realized; And finally integrating the original observation data, the behavior semantic map, the stage consistency index, the trusted interval and the trusted weight to form an enhanced data unit, and summarizing the enhanced data unit into an enhanced stage trusted data set.
6. The geological mineral exploration data processing method based on big data acquisition according to claim 5, wherein in step S3, the correlation network between the dynamic reconstruction data specifically comprises: Firstly, calculating initial association strength between any two data units by integrating a spatial distance function and an attribute similarity function based on the credibility weight, the spatial position coordinates and the attribute vector containing geophysical prospecting, chemical prospecting and engineering observation values of data units in an enhanced-stage credible data set; then introducing the cognitive evolution information in the exploration stage reflecting the revision information of the drilling verification result and the geological interpretation model, and generating a correlation influence factor; and dynamically modulating the initial association strength through the stage cognitive modulation coefficient to obtain the updated self-adaptive association strength.
7. The geological mineral exploration data processing method based on big data acquisition according to claim 6, wherein in step S3, performing adaptive sparsification processing on the association network specifically includes: dynamically determining a stage self-adaptive threshold based on the statistical distribution of all data of the current stage on the updated self-adaptive association strength so as to distinguish strong association edges from weak association edges; And for the edges identified as weak correlation, adopting a continuous edge weight attenuation strategy, and carrying out flexible weight reduction processing on the weights of the weak correlation edges through edge weight attenuation coefficients.
8. The geological mineral exploration data processing method based on big data acquisition according to claim 7, wherein in step S4, identifying stable local structural units specifically comprises: Based on the enhanced self-adaptive association data set, extracting a sparse association relation set between each data unit and other data units, and constructing a staged weighted association graph; calculating a structural stability index of each data unit, wherein the index is related to the weight sum of the associated edges and the stability of the neighborhood set; and under the constraint of space continuity, aggregating a plurality of data units with the structural stability index exceeding the local structural stability threshold to form a local structural unit.
9. The geological mineral exploration data processing method based on big data acquisition of claim 8, wherein in step S4, the adaptively determining the expression granularity of each structural unit specifically comprises: Calculating a granularity adaptation index of each local structural unit, wherein the index is obtained by integrating the internal average credible weight, the internal attribute difference degree and the current-stage mining task demand intensity index set by an engineering investigation plan of the structural unit through a granularity adaptation function; And according to the numerical value interval of the granularity adaptation index, adaptively selecting one expression granularity level of an original observation level, a structural feature level or a target decision level for the structural unit.
10. The geological mineral exploration data processing method based on big data acquisition according to claim 9, wherein in step S4, the standardized prospecting target expression unit generating process specifically comprises: According to the expression granularity level determined for each local structure unit, mapping the characteristics of each data unit in the structure unit by adopting a corresponding characteristic mapping function; According to the comprehensive contribution weight of each data unit, carrying out weighted fusion on the mapped characteristics to generate a granularity self-adaptive expression vector of the structural unit; And finally, integrating the granularity self-adaptive expression vector, the space coverage information of the structural unit and the overall credibility to construct a standardized prospecting target expression unit, and summarizing to form a stage prospecting target expression set.

Description

Geological mineral exploration data processing method based on big data acquisition Technical Field The invention relates to the technical field of geological mineral exploration and big data analysis and processing, in particular to a geological mineral exploration data processing method based on big data acquisition. Background Along with the continuous development of geological mineral exploration work, the means of remote sensing, geophysical prospecting, chemical prospecting, engineering cataloging and the like accumulate massive multi-source and multi-scale data, geological big data patterns are formed preliminarily, in recent years, the technologies of big data analysis, artificial intelligence and the like develop rapidly, and a new technical approach is provided for mining hiding rules from massive exploration data and improving prospecting prediction capability. The invention discloses a multi-source data processing system for big geographic information data, which relates to the technical field of data acquisition and sensors and comprises a data acquisition module, a distributed storage module, a data fusion module, an intelligent analysis module and a safety management module, wherein the data acquisition module is connected with remote sensing satellites, unmanned aerial vehicles, internet of things sensors and social media in real time through multi-source heterogeneous interfaces, the data format is self-adaptively analyzed and metadata marked, the distributed storage module is used for carrying out partition storage on the geographic information data based on a space-time database and an object storage architecture, and establishing dynamic space-time index and version control, and the data fusion module is used for realizing coordinate system conversion, time sequence calibration and semantic knowledge map matching based on a multi-source data alignment method of dynamic weight distribution. The current research trend is focused on deeper integration and collaborative analysis of investigation data of different sources and different stages, and explores how to more effectively integrate professional cognition and decision-making processes of investigation personnel into a calculation model so as to enhance the context perception and dynamic adaptability of data processing, under the background, how to construct an intelligent processing method which can adapt to the staged and progressive cognition characteristics of mineral exploration, realize multi-source information deep fusion, dynamic evolution of association relation and direct solidification of prospecting knowledge on a data layer, and is an important technical development direction, and aims to promote the new mode evolution of geological exploration from traditional experience driving to data and knowledge combined driving. Disclosure of Invention The invention aims to solve the problems in the background technology and provides a geological mineral exploration data processing method based on big data acquisition. The technical scheme of the invention is that the geological mineral exploration data processing method based on big data acquisition comprises the following concrete implementation steps: S1, synchronously extracting and structuring decision and cognitive hypothesis information expressing a current exploration stage in a multi-source exploration data acquisition process, converting the decision and cognitive hypothesis information into a stage behavior semantic vector and embedding the stage behavior semantic vector into a corresponding data unit to form a stage semantic constraint data set with cognitive background perception capability; S2, based on the staged semantic constraint data set, computing a stage cognition consistency index of data in a stage, dynamically generating a trusted interval, computing a trusted weight of each piece of data, and forming an enhanced stage trusted data set; S3, introducing a exploration stage cognitive evolution mechanism based on the enhanced stage trusted data set, dynamically reconstructing an association network between data, and performing self-adaptive sparsification processing on the association network to form an enhanced self-adaptive association data set; S4, identifying stable local structural units based on the enhanced self-adaptive associated data set, adaptively determining the expression granularity of each structural unit according to the demand of the prospecting task, generating corresponding multi-granularity characteristics, and finally integrating the expression granularity characteristics into a standardized prospecting target expression unit. Preferably, in step S1, the multi-source survey data includes: remote sensing image data, geophysical survey data, geochemical sampling data and engineering geological record data which are synchronously collected in the same investigation stage; Recording a phase identifier, a spatial position attribute and a collecti