Exploration right transfer block optimal selection method and system based on prospecting model

Abstract

The invention discloses a prospecting right transfer block optimization method and device based on a prospecting model, and the method comprises the steps: carrying out the extraction and standardized arrangement of a prospecting prediction model based on a geological report full-text database, and forming a prospecting model library containing metallogenic elements; semantic indexing and labeling are carried out on the geological data by utilizing the geologic structure position, the rock type and the metallogenic age elements in the prospecting model; converting the key prospecting mark in the prospecting model library into a quantitative matching condition in an XML format; performing analogical matching in the labeled geological data based on a quantitative matching condition, extracting coordinate information of a matching area and constructing a candidate block library; and automatically generating a block evaluation material and an important geological data list by combining the collected geological data according to the coordinate information in the candidate block library. According to the method, the geological prospecting model and the collection geological data can be effectively fused, rapid identification and systematic evaluation of the exploration right transfer block are realized, and the block optimization efficiency and the mineralization potential identification rate are remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for selecting exploration rights transfer blocks based on a mineral exploration model. Background Technology

[0002] Mineral resource security is a fundamental component of national security. Given the current complex and volatile international situation, there is an urgent need to increase the number of domestic exploration rights granted to establish a stable strategic reserve of mineral resources. Natural resources authorities need to expand the sources of granted blocks, rapidly evaluate the geological conditions of granted blocks, and significantly increase the number of blocks granted to meet the demands of the exploration market. However, traditional methods for predicting and selecting blocks through field geological prospecting are time-consuming and costly, making them difficult to meet market demands. For a long time, geological data collection mechanisms have enabled geological data repositories to accumulate massive amounts of geological data resources. Therefore, based on years of accumulated geological data, establishing a comprehensive technical system for selecting granted blocks, enabling a unified evaluation of multiple granted blocks in a "fast, efficient, and systematic" manner, has become an urgent need for the development of the modern mining market.

[0003] The existing technology lacks several shortcomings. First, it doesn't incorporate the prospecting models developed by field geologists, thus failing to inherit the experience of traditional geological prospecting. Second, the method eliminates restricted area data in its first step, resulting in the exclusion of many strategically valuable areas with mineralization potential, which can be used for strategic reserves but not for substantive development. Third, while the method utilizes data from 1:50,000 regional geological surveys, 1:50,000 regional mineral surveys, and the national mineral deposit database during the regional screening process, effectively identifying blocks with high levels of geological work, it also excludes a large number of blocks with high mineralization potential but low levels of geological work. Fourth, the technology fails to utilize geological report data. These are the inherent defects of this technical method. Summary of the Invention

[0004] This invention proposes a method for selecting exploration rights blocks based on a mineral exploration model. This method can effectively integrate geological exploration models with geological data from archives, enabling rapid identification and systematic evaluation of exploration rights blocks, and significantly improving the efficiency of block selection and the identification rate of mineral potential.

[0005] Another objective of this invention is to propose a device for selecting exploration rights transfer blocks based on a mineral exploration model.

[0006] To achieve the above objectives, a first aspect of the present invention proposes a method for selecting exploration rights transfer blocks based on a mineral exploration model, comprising: Based on the full-text database of geological reports, mineral exploration prediction models were extracted and standardized to form a mineral exploration model library containing mineralization elements. Integrate geological text data, spatial data, and map data, and use the geotectonic location, rock type, and metallogenic age elements in the mineral exploration model to perform semantic indexing and annotation on geological data; Convert key mineral exploration indicators in the mineral exploration model library into quantitative matching conditions in XML format; Based on quantitative matching conditions, analogical matching is performed on the labeled geological data to extract the coordinate information of the matching area and construct a candidate block library. Based on the coordinate information in the candidate block database, and combined with the geological data in the collection, the block evaluation materials and a list of important geological data are automatically generated.

[0007] In one embodiment of the present invention, the step of extracting and standardizing the mineral exploration prediction model based on the full-text database of geological reports to form a mineral exploration model library containing mineralized elements further includes: Use preset keywords to perform keyword searches in the full-text database of geological reports; Extract keyword search results and aggregate them to form a raw library of mineral exploration models; Data cleaning, organization, and standardization were carried out on the original mineral exploration model library to form a standardized mineral exploration model library.

[0008] In one embodiment of the present invention, the integration of geological text data, spatial data, and map data, and the semantic indexing and annotation of geological data using elements such as tectonic location, rock type, and metallogenic epoch in the mineral exploration model, further includes: Based on the 1:50,000 regional geological data in the collection, spatial data integration, sorting and splicing were carried out, and the data was converted into a searchable and retrieval format after code translation; Based on the full-text database of geological reports and geological raster map data, the geological reports are indexed and annotated using data items such as tectonic location, rock type, and metallogenic age in the mineral exploration model.

[0009] In one embodiment of the present invention, the step of converting key mineral exploration markers in the mineral exploration model library into quantitative matching conditions in XML format further includes: Based on a standardized mineral exploration model library, important mineral exploration indicator information is extracted to form a mineral exploration indicator library; Based on important mineral exploration indicators, XML format data query matching conditions are constructed.

[0010] In one embodiment of the present invention, the step of performing analogical matching on the labeled geological data based on XML matching conditions, extracting the coordinate information of the matching area, and constructing a candidate block library further includes: Based on XML format data matching conditions, query matching is carried out in the integrated and prepared spatial data, and the location coordinate information of the matching area is retained; Based on XML format data matching conditions, query and matching work is carried out in the geological reports and map data after indexing and annotation, the matching coordinate information is retained and supplemented to form a candidate block library.

[0011] In one embodiment of the present invention, it further includes: Based on the evaluation results in the candidate block library, strategic selection areas are distinguished from development selection areas. Strategic selection areas are marked and archived separately, while exploration rights transfer proposals are generated for development selection areas.

[0012] To achieve the above objectives, a second aspect of the present invention provides a device for selecting exploration rights transfer blocks based on a mineral exploration model, comprising: The model extraction and standardization module is used to extract and standardize mineral exploration prediction models based on the full-text database of geological reports, forming a mineral exploration model library containing mineralization elements. The data integration and semantic indexing module is used to integrate geological text data, spatial data and map data, and to semantically index and annotate geological data using the geotectonic location, rock type and metallogenic age elements in the mineral exploration model. The token conversion and XML generation module is used to convert key mineral exploration tokens in the mineral exploration model library into quantitative matching conditions in XML format. The analogy matching and candidate library construction module is used to perform analogy matching on labeled geological data based on quantized matching conditions, extract coordinate information of matching areas and construct a candidate block library. The material generation and list construction module is used to automatically generate block evaluation materials and a list of important geological data based on the coordinate information in the candidate block library and the geological data in the collection.

[0013] The proposed invention provides a method and apparatus for selecting exploration rights blocks based on a mineral exploration model. By integrating the mineral exploration model with geological data, it enables rapid identification and evaluation of exploration rights blocks, improves the efficiency of block selection and the identification rate of mineral potential, effectively inherits traditional mineral exploration experience, and reduces exploration costs.

[0014] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0015] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 A flowchart of a method for selecting exploration rights transfer blocks based on a mineral exploration model, provided in an embodiment of the present invention; Figure 2This invention provides an architecture diagram of a prospecting rights transfer block selection system based on a prospecting model, as provided in an embodiment of the invention. Figure 3 This is a structural diagram of a mineral exploration rights transfer block selection device based on a mineral exploration model, provided in an embodiment of the present invention. Detailed Implementation

[0016] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0017] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0018] The following describes, with reference to the accompanying drawings, a method and system for selecting exploration rights transfer blocks based on a mineral exploration model, according to an embodiment of the present invention.

[0019] This embodiment provides a method for selecting the optimal exploration rights transfer block based on a mineral exploration model. For example... Figure 1 As shown, it includes: S101, based on the full-text database of geological reports, extracts and standardizes mineral exploration prediction models to form a mineral exploration model library containing ore-forming elements. Specifically, this invention aims to construct a structured and reusable mineral exploration model library to provide a scientific basis for subsequent block selection. The technical implementation principle of this step is based on a combination of natural language processing (NLP) and data standardization processing. Through processes such as keyword retrieval, information extraction, and data cleaning, mineralized elements and mineral exploration prediction models are systematically extracted from geological reports.

[0020] In some implementations, the first step is to use keywords such as "mineral exploration model," "mineral exploration prediction model," "metallogenic model," "metallogenic elements," "mineral exploration elements," "prediction elements," and "mineral exploration pattern" to perform a full-text search in a geological report full-text database. This search process can employ text retrieval algorithms such as TF-IDF and BM25, combined with a geological industry terminology dictionary, to improve the accuracy and recall of the search. Search results are typically output in the form of metadata such as document ID, paragraph position, and keyword matching degree.

[0021] Subsequently, the system extracts information from the retrieved text content, identifying and aggregating key information such as mineralization elements, prospecting indicators, and mineralization conditions. This process can employ techniques such as rule matching, named entity recognition (NER), and relation extraction to extract structured fields such as "rock type," "tectonic environment," and "mineralization type." The extraction results are stored in JSON or XML format, forming the original library of prospecting models.

[0022] Furthermore, the system cleans and standardizes the data in the original database. The cleaning process includes removing duplicate records, correcting spelling errors, and standardizing terminology. Standardization, based on national standards such as the "Technical Specifications for Mineral Resources Exploration" (GB / T13908-2013), classifies and codes the ore-forming elements in the model. For example, "sedimentary rock" is standardized as `rock_type: 1`, and "hydrothermal deposit" is standardized as `ore_type: 2`. This ultimately forms a mineral exploration model library with standardized fields and expressions, providing a data foundation for subsequent analogy matching and block selection.

[0023] This step plays a crucial role in the overall technical solution. The mineral exploration model library it constructs not only inherits traditional geological prospecting experience but also provides structured data support for subsequent automated matching and evaluation. Through standardization, the comparability and consistency of the models across different geological reports are ensured, improving the scientific rigor and efficiency of block selection.

[0024] Furthermore, S101 includes: S1011 uses keywords such as "mineral exploration model", "mineral exploration prediction model", "metallogenic model", "metallogenic elements", "mineral exploration elements", "prediction elements", and "mineral exploration pattern" to conduct keyword retrieval of the full-text database of geological reports.

[0025] Specifically, this invention employs keyword-based full-text retrieval technology to systematically mine full-text databases of geological reports in order to extract textual information related to mineral exploration models. The technical implementation principle of this step is based on Natural Language Processing (NLP) and Information Retrieval (IR) technologies. By constructing a multi-dimensional keyword set, it achieves the identification and extraction of implicit mineral exploration models from geological reports.

[0026] The specific operation method is as follows: First, define a set of keywords with semantic features of geological prospecting, including "prospecting model," "prospecting prediction model," "metallogenic model," "metallogenic elements," "prospecting elements," "predictive elements," and "prospecting pattern." These keywords are based on commonly used terms in the theoretical system of geological prospecting, have clear geological semantic orientation, and can effectively characterize the prospecting model information that may be included in the geological report. In some implementations, a synonym expansion mechanism can be further introduced, such as "metallogenic conditions" and "mineralization characteristics," to improve the coverage and recall rate of the search.

[0027] Secondly, a full-text search engine (such as Elasticsearch, Solr, etc.) is used to index and match keywords in the full-text database of geological reports. During the search process, Boolean logic combination conditions (such as AND, OR, NOT) can be set to achieve combined keyword matching. For example, "mineral exploration model AND ore-forming elements" can be set as a composite search condition to improve the accuracy of search results. At the same time, the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm can be introduced to calculate the weight of keywords in documents, thereby filtering out geological reports that are highly relevant to the mineral exploration model.

[0028] The retrieval process allows setting a minimum matching frequency threshold (e.g., ≥2 times) to filter out low-relevance documents; simultaneously, a document length limit (e.g., ≥5000 words) can be set to ensure the extracted content contains sufficient information. Furthermore, N-gram models (e.g., bigram, trigram) can be introduced to identify the contextual semantics of keywords, further improving the semantic accuracy of the model's extraction.

[0029] This step plays a crucial role in the overall technical solution and is the foundation for building a mineral exploration model library. By systematically extracting mineral exploration model information from geological reports, it not only inherits traditional geological prospecting experience but also provides structured and standardized data support for subsequent analog matching and block selection. In practical applications, this step can be deployed in a geological data management system, combined with distributed computing frameworks (such as Hadoop and Spark) to achieve efficient processing of large-scale geological reports. It is suitable for natural resource authorities or mining enterprises to quickly identify potential mineral exploration models from massive amounts of geological data, thereby improving the intelligence level and efficiency of block selection.

[0030] S1012, Extract the keyword search results and aggregate them to form the original library of mineral exploration models. Specifically, "extracting the search results of the above keywords and aggregating them to form the original library of mineral exploration models" is the key step in building the mineral exploration model library. Its technical implementation is based on natural language processing (NLP) and information extraction technology. It aims to efficiently extract text content related to mineral exploration models from the full-text database of geological reports and perform preliminary aggregation and structuring processing to lay the foundation for subsequent data cleaning and standardization.

[0031] In some implementations, this step first involves using a full-text database retrieval system to perform full-text matching retrieval using a pre-defined set of keywords (such as "mineral exploration model," "mineral exploration prediction model," "metallogenic model," "metallogenic elements," "mineral exploration elements," "prediction elements," "mineral exploration pattern," etc.). Keyword matching can employ text retrieval algorithms such as TF-IDF and BM25, or context-aware keyword recognition using deep learning-based semantic matching models (such as BERT and RoBERTa) to improve retrieval accuracy and recall. Retrieval results typically include metadata information such as document title, body paragraphs, and page number positions.

[0032] Optionally, the system can set matching thresholds, such as keyword frequency of at least 3 times or contextual semantic relevance score higher than 0.75, to filter out low-relevance content. Furthermore, to improve information aggregation efficiency, the system can perform cluster analysis on the matching results to identify mineral exploration model descriptions with similar semantic structures, thereby avoiding repeated extraction and redundant storage.

[0033] Key technical parameters involved in this step include: keyword matching algorithm type, matching threshold, text extraction granularity (e.g., paragraph or sentence level), clustering algorithm (e.g., K-means, DBSCAN) and its similarity calculation method (e.g., cosine similarity, Jaccard coefficient). Furthermore, it is necessary to comply with national or industry standards such as the "Standardization Specification for Geological Data" (GB / T 32468-2015) to ensure the uniformity of the extracted content's format and semantic consistency.

[0034] This step is widely used in the mineral resource management work of geological data archives or natural resource authorities. By automatically extracting and aggregating descriptions of mineral exploration models from geological reports, a preliminary original library of mineral exploration models can be quickly built, providing data support for subsequent model standardization, analog matching, and block selection.

[0035] The technical effect of this step is that it enables the systematic extraction of mineral exploration model information implicit in geological reports, effectively improves the construction efficiency and data quality of the mineral exploration model library, and provides a structured and searchable data foundation for subsequent model-based block selection, thereby enhancing the application value of geological data in mineral resource evaluation.

[0036] S1013 involves cleaning, organizing, and standardizing the original mineral exploration model library to create a standardized mineral exploration model library.

[0037] Specifically, cleaning, organizing, and standardizing the original mineral exploration model library is a crucial step in building a standardized mineral exploration model library. This step aims to eliminate redundancy, errors, and inconsistencies in the original data, ensuring data quality and consistency in subsequent model matching and block selection processes.

[0038] Data cleaning includes denoising the raw text data, such as removing irrelevant characters, punctuation marks, duplicate paragraphs, and formatted errors. Simultaneously, geological terminology is standardized, for example, unifying different expressions like "ore-forming elements" and "mineral exploration elements" into standard terms to improve data searchability and semantic consistency. The data processing involves reconstructing the model structure, converting unstructured or semi-structured text information into structured data, typically organized using XML or JSON formats for easier subsequent automated processing and matching. Standardization work involves uniformly naming and classifying the model's attribute fields according to industry standards (such as the "Technical Specifications for Mineral Resource Exploration" and the "Geological Survey Results Data Standards") to ensure good compatibility and scalability of the model library across different geological regions and data sources.

[0039] During the cleaning process, a text length threshold needs to be set (e.g., a minimum of 500 valid characters) to remove fields with null values ​​or a missing value rate exceeding 80%. During standardization, unified field naming rules need to be defined (e.g., "rock_type", "tectonic_setting", "mineralization_age", etc.), and field data types (e.g., string, integer, floating-point) and value ranges (e.g., limiting the mineralization age to geological time units, such as "Cambrian", "Jurassic", etc.). Furthermore, a terminology mapping table needs to be established to map terms from different geological reports to a unified geological terminology system.

[0040] This step is widely used by geological data archives, natural resource authorities, and mining companies. By building a standardized mineral exploration model library, a high-quality data foundation can be provided for subsequent analog matching, block screening, and evaluation. It is especially suitable for areas with high mineralization potential but low levels of geological work, avoiding information omissions due to non-standard data.

[0041] The technical effect of this step is that it significantly improves the availability and consistency of mineral exploration model data, providing reliable data support for subsequent automated matching and block selection, thereby achieving efficient and systematic selection of non-oil and gas mineral exploration rights transfer blocks.

[0042] S201 integrates geological text data, spatial data, and map data, and uses elements such as tectonic location, rock type, and metallogenic age in the mineral exploration model to perform semantic indexing and annotation of geological data.

[0043] Specifically, integrating and preparing geological text data, geological spatial data, and geological map data, and carrying out semantic indexing and annotation of geological report texts and maps for mineral exploration prediction models, is a key step in this invention to achieve "rapid, efficient, and systematic" selection of exploration rights blocks. This step, through the fusion processing of multi-source heterogeneous geological data, constructs a unified data semantic structure, thereby providing a high-quality data foundation for subsequent analogy matching and block selection.

[0044] In some implementations, this step begins with the integration and organization of spatial data based on the archive's 1:50,000 regional geological data. Specific operations include unifying the coordinate system (e.g., to the CGCS2000 coordinate system) of spatial data from different sources and formats, layer stitching, and attribute field standardization. After code transcoding, the spatial data is transformed into a structured format supported by database systems, such as GeoJSON or Shapefile, and spatial indexing techniques (e.g., R-tree indexes) are used to improve subsequent query efficiency.

[0045] Furthermore, semantic indexing and annotation were conducted on the full-text database of geological reports and geological raster map data, utilizing core elements of the mineral exploration model—tectonic location, rock type, and metallogenic epoch. In terms of text data processing, Natural Language Processing (NLP) technology was employed, combined with geological ontology and Named Entity Recognition (NER) models, to identify and classify key terms in the geological reports. For example, tectonic location could be identified as "North China Plate" or "South China Fold Belt"; rock type as "granite" or "basalt"; and metallogenic epoch as "Cambrian" or "Jurassic," mapping them to unified geological classification standards (such as the "Chinese Rock Classification and Naming Scheme" and the "Chinese Geological Time Division Standard").

[0046] In terms of map data processing, image recognition and GIS spatial analysis technologies are used to automatically identify and vectorize rock distribution, structural features, and mineralization zones in geological maps. By combining geological elements from the mineral exploration model, key areas in the maps are semantically annotated to form structured map metadata, which facilitates subsequent XML format querying and matching.

[0047] This step relies on key technologies such as standardized processing of multi-source data, semantic parsing, and spatial information extraction. Its core parameters include spatial resolution (e.g., a 1:50,000 scale), text annotation accuracy (typically required to be ≥85%), and map recognition accuracy (e.g., ≥90%). This step effectively integrates geological text and map information, providing structured and semantic data support for subsequent analogical matching, thereby significantly improving the intelligence level and data utilization rate of block selection.

[0048] Furthermore, S201 includes: S2011, based on the 1:50,000 regional geological data in the collection, carried out spatial data integration, sorting and splicing, and after code translation, formed a searchable data format.

[0049] Specifically, based on the 1:50,000 regional geological data in the collection, spatial data integration, organization, and splicing are carried out. After code translation, the data is formed into a searchable and retrieval-enabled format. This is a key step in the systematic processing of geological data and block selection in this invention. This step mainly focuses on the standardization and structuring of geological spatial data, providing a unified and operable data foundation for subsequent analog matching and block selection based on mineral exploration models.

[0050] This step begins by integrating spatial data from the collection, including 1:50,000 geological maps and geological survey results. The integration process involves unifying the spatial coordinate system (e.g., adopting the CGCS2000 coordinate system), standardizing the layer structure (e.g., following the "Geological Layer Data Structure Specification" GB / T 21748-2008), and converting spatial data formats (e.g., converting original CAD and GeoTIFF formats to GeoJSON or Shapefile formats). Subsequently, geological maps from different regions are stitched together using spatial topology verification and boundary alignment algorithms (e.g., the `gdal_merge.py` tool based on GDAL or the Mosaic tool in ArcGIS) to ensure seamless spatial connection between adjacent map sheets and eliminate data silos.

[0051] During spatial data stitching, a certain tolerance threshold (e.g., 0.5 meters to 5 meters) needs to be set to handle boundary inconsistencies caused by errors in coordinate systems of different map sheets or differences in acquisition accuracy. In the code translation stage, XML or JSON format is used to structurally encode the attribute information in geological maps. For example, fields such as rock type, structural features, and mineralization information are mapped to standard metadata tags to ensure that the data has good semantic searchability and machine readability.

[0052] This step is widely used by geological data archives, natural resources authorities, and mining companies to build a unified geological spatial database and support block selection systems based on mineral exploration models. Data processed through this step can be directly used for spatial queries, layer overlay analysis, and mineralization condition matching, providing structured and searchable geological spatial data support for subsequent operations.

[0053] This step enabled the systematic integration and standardized processing of geological spatial data, improving data availability and consistency, and providing a reliable data foundation for automated matching based on mineral exploration models. Simultaneously, code translation endowed geological map information with structured features, facilitating subsequent computer processing and information mining, thereby significantly improving the efficiency and accuracy of block selection.

[0054] S2012, based on the full-text database of geological reports and geological raster map data, uses data items such as tectonic location, rock type, and metallogenic age in the prospecting model to carry out indexing and annotation work on geological reports.

[0055] Specifically, this invention, based on a full-text database of geological reports and geological raster map data, utilizes key geological elements in mineral exploration models—such as tectonic location, rock type, and metallogenic epoch—to index and annotate geological reports. The core of this step lies in structurally associating geological textual information with spatial map data, thereby providing high-quality semantic and spatial data support for subsequent analogical matching and block selection.

[0056] This step begins with extracting information from the full-text database of geological reports using Natural Language Processing (NLP) technology. Specifically, an entity recognition method combining rule-based and machine learning is employed to identify key geological elements in the text, such as tectonic locations (e.g., plate boundaries, tectonic zones, fault systems), rock types (e.g., granite, basalt, sedimentary rocks), and metallogenic epochs (e.g., Cambrian, Jurassic, Cenozoic). Simultaneously, spatial information is extracted from the geological raster map data, including parameters such as coordinate system (e.g., WGS-84, CGCS2000), spatial resolution (e.g., a spatial accuracy of 50 meters per pixel for a 1:50,000 scale map), and map type (e.g., geological mapping, mineral prediction maps, tectonic maps). By mapping textual information to map coordinates, structured indexing of the geological report content is achieved.

[0057] This invention standardizes key parameters in the indexing process. For example, the indexing of tectonic locations must conform to the "Standard for Division of Tectonic Units in China" (GB / T 17766-2017), the indexing of rock types must refer to the "Rock Classification and Nomenclature Standard" (DZ / T 0221-2006), and the indexing of metallogenic epochs must be based on the "Standard for Geological Time Division" (GB / T17765-2017). Furthermore, the coordinate accuracy of the map data must meet the 1:50,000 scale cartographic standard to ensure accurate spatial matching.

[0058] This step is widely applicable to geological data archives, natural resources authorities, and mining enterprises. By uniformly indexing historical geological reports and map data, it enables rapid identification and information integration of areas with mineralization potential, providing a data foundation for subsequent block selection and transfer decisions. Especially in areas with low levels of geological work but high mineralization potential, this step can effectively preserve information and avoid missing strategic selection areas due to data exclusion.

[0059] By introducing key geological elements from the mineral exploration model, deep integration of geological text and map data was achieved, enhancing the semantic retrieval and spatial matching capabilities of geological data. Furthermore, it provided structured and standardized data input for subsequent analogical matching and block evaluation, thereby significantly improving the efficiency and scientific rigor of block selection.

[0060] S301 converts key mineral exploration indicators in the mineral exploration model library into quantitative matching conditions in XML format.

[0061] Specifically, converting key mineral exploration indicators from the mineral exploration model library into quantitative matching conditions in XML format is the core step in achieving efficient and structured matching between geological data and mineral exploration models. This step formalizes the mineral exploration indicators extracted from the experience of geological experts, thereby providing standardized and executable query conditions for subsequent automatic or semi-automatic data matching.

[0062] In some implementations, this step first extracts key elements with mineralization indicative significance from a constructed library of standardized mineral exploration models, such as tectonic location, rock type, metallogenic epoch, mineralization type, and ore-controlling structures. These elements typically exist in the form of text, classification codes, or numerical ranges and require further quantification. For example, the metallogenic epoch can be converted into a numerical range of geological ages (e.g., Rock types can be mapped to rock classification codes (such as GB / T 17412-1998 "Rock Classification and Naming Standard"), and ore-controlling structures can be represented as a combination of structural types and spatial distribution conditions.

[0063] Furthermore, these quantified mineral exploration indicators need to be converted into XML query conditions, adhering to certain structured standards. In the XML document, each mineral exploration indicator is a node, containing attributes such as `type` (indicator type), `value` (specific value), `operator` (comparison operator, such as "=", ">=", "in", etc.), and `weight` (matching weight, used for weighted calculations in subsequent evaluation models, such as...). For example, a typical XML matching condition node can be represented as: ```xml <criterion type="rock_type" value="5301" operator="in" weight="0.3" / > ``` Here, `rock_type` represents the rock type flag, `value` is the rock classification code, `operator` represents the matching method for this flag, and `weight` represents its weight coefficient in the overall matching.

[0064] In practical applications, this step typically runs within the query engine of a geological data database, supporting structured retrieval based on XML criteria. By converting prospecting indicators into executable XML query conditions, the system can automatically identify geological maps, text reports, or spatial data that meet the conditions, thereby quickly filtering out candidate blocks with mineralization potential.

[0065] The technical advantage of this step lies in achieving semantic mapping and logical matching between mineral exploration models and geological data, thereby improving the automation and matching accuracy of block selection. Furthermore, by introducing weight parameters, it can further support comprehensive evaluation of multiple factors, providing a scientific basis for subsequent block selection and strategic reserves.

[0066] Furthermore, S301 includes: S3011, based on a standardized mineral exploration model library, extracts important mineral exploration indicator information to form a mineral exploration indicator library.

[0067] Specifically, based on a standardized mineral exploration model library, extracting key mineral exploration indicator information to form a mineral exploration indicator library is one of the core steps in the technical solution of this invention to achieve optimal geological data and block analogy matching. This step aims to extract key mineral exploration indicators from standardized mineral exploration models, construct a structured and searchable mineral exploration indicator library, and provide basic support for subsequent geological data matching and block selection.

[0068] This step first involves semantic parsing and feature extraction of the established standardized mineral exploration model library. The library typically contains key elements such as metallogenic geological conditions, mineralization type, deposit size, ore-controlling structures, mineralization indicators, geochemical anomalies, and geophysical characteristics. Through Natural Language Processing (NLP) and geological semantic analysis techniques, the system can identify and extract mineral exploration indicators from these elements, such as "magmatic hydrothermal deposits," "fault-controlled ore," and "Au-Ag multi-element anomalies." Further, the system classifies, encodes, and standardizes these indicators to form a unified mineral exploration indicator library structure, typically including fields such as indicator category (e.g., structural indicators, rock indicators, geochemical indicators), indicator name, indicator description, and indicator weight.

[0069] The extraction and refinement of mineral exploration indicators must be based on geological industry standards (such as the "Technical Specification for Mineral Resources Exploration" GB / T13908-2013) and the results of metallogenic regularity research. Each indicator in the indicator library needs to have its importance weight assigned in the mineral exploration model. The weight value is usually in the range [0, 1], representing the degree of contribution of the indicator to the mineralization probability. For example, for the indicator "fault zone controlling ore deposits," its weight can be set to... For the "mineralization alteration zone" indicator, the weight can be set to... These weight values ​​can be set based on expert experience or statistical analysis of historical mineral exploration cases.

[0070] This step is widely used in the selection of exploration rights blocks for non-oil and gas mineral deposits. By constructing a mineral exploration indicator database, the system can automatically match and filter geological texts, maps, and spatial data, thereby quickly identifying areas with similar metallogenic backgrounds. For example, identifying tectonic environments, rock assemblages, and geochemical characteristics similar to known deposits in regional geological maps can provide a scientific basis for the selection of candidate blocks.

[0071] This step effectively improves the operability of the mineral exploration model and the accuracy of data matching. By transforming the experience of geological experts into structured, computable mineral exploration indicators, the system can achieve efficient utilization of geological data, making up for the shortcomings of traditional methods in utilizing geological report information. At the same time, this step provides standardized input for the subsequent construction of XML-formatted matching conditions, enhancing the automation and consistency of the entire optimization process.

[0072] S3012, based on important mineral exploration indicators, construct XML format data query matching conditions.

[0073] Specifically, constructing XML-formatted data query matching conditions based on a standardized mineral exploration model library is a key step in achieving efficient retrieval and analogical matching of geological data. The core of this step lies in structurally representing the important mineral exploration indicators extracted from the models and transforming them into query conditions that can be parsed and executed by a computer system, thereby achieving accurate matching of geological text, spatial data, and map data.

[0074] In some implementations, this step first extracts geological elements with mineralization indicative significance from the established mineralization indicator database, such as tectonic location, rock type, metallogenic epoch, mineralization type, and ore-controlling structures. These elements typically exist in the form of text, classification codes, or numerical ranges. To achieve unified querying across data sources, these elements need to be mapped to structured fields defined in XMLSchema, and corresponding query logic expressions need to be set. For example, the metallogenic epoch can be represented as ` <mineralizationepoch>Its value can be a standardized name of a geological era (such as "Mesozoic", "Cenozoic", etc.), and it supports range queries, such as ` <mineralizationepoch> <from> 145< / from> <to> 66< / to> < / mineralizationepoch> ` indicates the Cretaceous period.

[0075] Furthermore, the construction of XML query conditions must adhere to certain standards and specifications, such as ISO 19139 (Geographic Information Metadata Standard) or GB / T 19710-2005 (Geological Data Metadata Standard), to ensure data interoperability and retrievability. Additionally, XPath expressions or SQL-like syntax can be optionally introduced to support complex conditional queries, such as ` / / MineralizationEpoch[text()='Mesozoic'] ​​and / / RockType[contains(., 'Granite')]`, used to match geological data that simultaneously satisfies both "Mesozoic mineralization epoch" and "rock type includes granite".

[0076] The technical advantage of this step lies in its ability to efficiently screen and match geological data by transforming mineral exploration indicators into structured query conditions, providing standardized and executable input for subsequent data matching. Simultaneously, this method avoids the subjectivity and inefficiency of traditional manual screening, improving the automation and scientific rigor of block selection. It is a crucial support for achieving the "fast, efficient, and systematic" selection objective of this invention.

[0077] S401, based on the XML matching conditions, perform analog matching in the labeled geological data, extract the coordinate information of the matching area, and construct a candidate block library.

[0078] Specifically, analogical matching based on XML format data matching conditions in labeled geological data is one of the core steps in achieving block selection. This step involves structurally matching the constructed XML matching conditions with prepared and labeled geological text data, spatial data, and map data to extract regional coordinate information with similar mineral exploration geological features and construct a candidate block library.

[0079] In some implementations, XML matching criteria are structured expressions based on key mineral exploration indicators (such as tectonic location, rock type, and metallogenic epoch) extracted from a mineral exploration model library. Each matching criterion corresponds to a combination of one or more geological features, for example: ,in This indicates the matched mineralized region. , , These represent sets of matching conditions for rock type, tectonic environment, and metallogenic epoch, respectively. Through the node structure of XML, precise matching and logical combination of multidimensional geological features can be achieved.

[0080] In practice, the system first performs queries and matching within the constructed spatial data, retaining the coordinate information of regions that meet the XML conditions. Subsequently, from the completed geological text and map data, it further extracts the coordinate information of geological reports and maps that match the matching conditions, and merges this information with the spatial data matching results to form a complete candidate block library. This process typically employs XML query languages ​​such as XPath or XQuery for efficient retrieval, ensuring the accuracy and scalability of the matching.

[0081] In application scenarios, this step is widely used by natural resource authorities or mining companies for the rapid screening of potential mineralized areas. Automated matching significantly reduces the workload of manual screening and improves the efficiency of block selection. For example, in 1:50,000 geological map data, the system can identify areas that highly match the target mineral exploration model and output their geographic coordinate range (such as latitude and longitude intervals in the WGS-84 coordinate system) for subsequent evaluation.

[0082] The technical advantage of this step lies in its ability to efficiently identify and integrate potential mineralized areas from geological data through structured analogy matching, providing a data foundation for subsequent block evaluation. Simultaneously, this method preserves areas with lower levels of geological work but high mineralization potential, overcoming the shortcomings of prematurely eliminating restricted areas in existing technologies and enhancing the scientific rigor and comprehensiveness of block selection.

[0083] Furthermore, S401 includes: S4011, based on XML format data matching conditions, performs query matching in the integrated and prepared spatial data, and retains the location coordinate information of the matching area.

[0084] Specifically, the system performs query matching based on XML format data matching conditions within the integrated and prepared spatial data, and retains the location coordinates of the matching areas. This step is a crucial link in the entire optimization method for achieving accurate data filtering and spatial positioning, and its technical implementation relies on structured data processing, spatial database query mechanisms, and the spatial analysis capabilities of Geographic Information Systems (GIS).

[0085] In some implementations, this step first imports the constructed XML-formatted query criteria into a spatial database system, such as PostGIS or ArcGIS Geodatabase. The XML file typically contains multiple structured fields, such as tectonic location (…). ), rock type ( Metallogenic Age ( Each field corresponds to one or more matching rules, such as "contains a certain type of tectonic environment", "rock type is granite", "mineralization age is Late Jurassic to Early Cretaceous".

[0086] Furthermore, the system performs conditional matching on spatial data using SQL statements or spatial query languages ​​(such as SPARQL and GeoSPARQL). For example, it uses spatial functions such as `ST_Intersects` or `ST_Within`, combined with the geographical extent defined in XML. This allows you to filter regions in spatial data that meet certain criteria using coordinate systems (such as CGCS2000 or WGS84). The query results will retain the geometric information of the matching regions (such as polygon coordinates, area, center point coordinates, etc.) and be output in GeoJSON or Shapefile format.

[0087] Optionally, the system can also set matching threshold parameters, such as the minimum number of matching fields ( ), field matching weight ( This allows for improvements in matching accuracy and flexibility. For example, if five mineral exploration marker fields are defined in the XML, the system can be configured to retain only regions that match at least three of these fields, thus preventing low-relevance data from interfering with the optimal results.

[0088] In practical applications, this step is typically deployed in geological data centers or natural resource management platforms to quickly filter out areas that match mineral exploration models from massive amounts of spatial data. Its technical advantage lies in significantly improving the efficiency and accuracy of block selection, providing reliable spatial data support for subsequent geological evaluation and transfer decisions.

[0089] S4012, based on XML format data matching conditions, performs query matching work in the geological reports and map data after indexing and annotation, retains the matching coordinate information and supplements it into the S4011 results to form a candidate block library.

[0090] Specifically, based on XML format data matching conditions, query and matching work is carried out in geological reports and map data that have been indexed and annotated. Its core is to achieve accurate identification and extraction of potential mineral exploration information in geological texts and maps through a structured data retrieval mechanism, and to supplement the coordinate information in the matching results into the matching results of S4011, thereby constructing a more comprehensive candidate block library.

[0091] This step first relies on the indexing and annotation of geological reports and map data. The indexing and annotation process typically involves entity recognition of the text content (such as metallogenic epoch, rock type, tectonic features, etc.) and mapping it to tag elements in an XML structure. For example, the information about "metallogenic epoch" mentioned in a geological report would be annotated as `<meta>`.<mineralization_period> The content can be "Late Jurassic" or "Cretaceous," etc. The map data is then extracted using spatial information extraction tools, converting geological units, mineralization zones, structural lines, and other elements from the map into XML format.<geological_unit> `、`<mineralized_zone> `、`<structural_line> Tags such as `, along with their spatial coordinate information, such as ` <coordinates> 40.01, 116.32< / coordinates> `.

[0092] The system applies the constructed XML-formatted query criteria to the aforementioned structured geological report and map data. Query criteria typically include multiple logically combined XML tags and their attribute values, such as ` and ,in and These represent the mineralization age and rock type parameters, respectively. and This indicates the matching range defined in the mineral exploration model. By matching the data using an XML parser (such as XPath or XQuery), the system can extract geological units or mineralized zones that meet the requirements of the mineral exploration model and record their spatial coordinate information.

[0093] The construction of XML query conditions must comply with geographic information metadata standards such as ISO 19115 and ISO 19139 to ensure the compatibility and searchability of the data structure. Meanwhile, parameters such as similarity thresholds and field weights in the matching process can be dynamically configured according to the prospecting models for different mineral types. For example, the matching weight for mineralization age can be set to 0.3, rock type to 0.4, and tectonic environment to 0.3, to achieve differentiated processing of different prospecting elements.

[0094] This step is widely used by natural resources authorities in the selection of blocks before the granting of exploration rights for non-oil and gas minerals. By automatically matching key mineral exploration information in geological reports and maps, areas with mineral potential but not included in traditional methods can be quickly identified, providing data support for the selection of strategic reserve blocks.

[0095] By efficiently matching XML structured data, the system can systematically mine the mineral exploration information hidden in geological data, improve the accuracy and efficiency of block selection, make up for the shortcomings of existing technologies that do not make full use of geological report data, and provide a solid data foundation for subsequent block evaluation and transfer decisions.

[0096] S5 automatically generates block evaluation materials and a list of important geological data based on the coordinate information in the candidate block library and the geological data in the collection.

[0097] Specifically, based on the coordinate information in the candidate block library and combined with the catalog of geological data in the archive, the system automatically generates block evaluation materials and a list of important geological data. This step is a key link in achieving the evaluation goals of "fast, efficient, and systematic" in the entire optimization method. Its technical implementation principle is based on the fusion processing of spatial and textual data, as well as an automated information extraction and recombination mechanism.

[0098] In some implementations, this step first uses a spatial coordinate matching mechanism to filter various types of geological data from the archive's geological data catalog that intersect with or contain the spatial extent of the candidate block. These include regional geological survey reports, mineral exploration reports, geophysical and geochemical data, and remote sensing imagery. This data is typically stored in vector formats (such as GeoJSON and Shapefile) or raster formats (such as TIFF and JPEG), along with metadata descriptions including data type, acquisition time, work progress, and mineralization type. The system uses spatial indexing techniques (such as R-trees and quadtrees) to achieve efficient spatial retrieval, ensuring rapid location of relevant data within large-scale datasets.

[0099] Furthermore, the system employs Natural Language Processing (NLP) and structured data parsing techniques to automatically extract information such as transportation location, past geological work, and mineral exploration information from the matched geological data. Transportation location information includes distances to the nearest highways, railways, and airports, as well as accessibility assessments; past geological work information includes the time, organization, methods, and results of each exploration activity; and mineral exploration information involves mineralization characteristics, ore body size, mineral type, and metallogenic conditions. This information is extracted from unstructured text and stored in a structured manner using techniques such as entity recognition, relation extraction, and semantic annotation.

[0100] Based on the extracted information, the system automatically generates standardized proposals and geological evaluation forms for the transfer of blocks. The proposals include basic block information, mineralization potential analysis, and assessments of transportation and working conditions; the geological evaluation forms are filled in according to national standards such as the "Specification for Evaluation of Mineral Resources Exploration Blocks" (GB / T 33444-2016). Simultaneously, based on the data type and importance contained in the data package, the system automatically generates a list of important geological data, including data name, number, source unit, data format, spatial range, and mineralization information summary, facilitating subsequent data retrieval and management.

[0101] The technical advantage of this step lies in its ability to significantly improve the efficiency of generating block evaluation materials through automation and semi-automation, while reducing the workload of manual compilation and writing. Simultaneously, the standardized output format ensures the uniformity and comparability of the evaluation materials, providing natural resources authorities with a scientific and standardized basis for decision-making, thereby enabling rapid selection and efficient management of exploration rights blocks.

[0102] It also includes S601, which, based on the evaluation results in the candidate block library, distinguishes between strategic and development zones, marks and archives strategic zones separately, and generates exploration rights transfer proposals for development zones.

[0103] Specifically, based on the evaluation results in the candidate block library, blocks are classified into strategic and developmental selection areas, and then labeled, archived, and have proposals generated for each. This is a key step in the technical solution of this invention to achieve block selection and strategic resource deployment. This step, through systematic data processing and classification logic, ensures that natural resource authorities can efficiently identify strategically significant blocks and provide a scientific basis for subsequent exploration rights grants.

[0104] This step first involves a comprehensive evaluation of each block's mineralization potential, geological work progress, and regional constraints based on the extracted geological data packages from the candidate block database. The evaluation process employs a combination of semi-automation and automation, using Natural Language Processing (NLP) technology to extract key information from geological reports, such as transportation location, past geological work, and mineral exploration information, and then structuring this information into quantifiable indicators. For example, transportation location information can be converted into the straight-line distance to the nearest road or railway. Previous geological work can be classified according to the level of work. Values ​​are assigned, and mineral exploration information is obtained by matching feature items in the mineral exploration indicator library. Perform weighted scoring.

[0105] The criteria for determining strategic selection areas typically include mineral potential scoring. Higher than the set threshold And the degree of geological work Lower, or located in the restricted area Internally, development zones must meet the following requirements. and This means that the geological work foundation is relatively good and there are no policy restrictions. By setting multi-dimensional evaluation indicators, the system can automatically classify candidate blocks.

[0106] This step applies to the data processing workflow of natural resources authorities in mineral resource strategic planning and exploration rights transfer decisions. By separately archiving strategic selection areas, data support can be provided for national mineral resource strategic reserves; while generating exploration rights transfer proposals for development selection areas helps to promote the activity of the exploration market and improve resource utilization efficiency.

[0107] The technical effect of this step is that it enables refined classification and management of candidate blocks, improves the scientific and systematic nature of block selection, and takes into account both strategic reserves and market development needs, providing efficient and traceable technical means for mineral resource management.

[0108] The prospecting rights transfer block selection method based on prospecting model in this invention systematically integrates and matches prospecting model and geological data to achieve rapid selection and evaluation of non-oil and gas mineral prospecting rights transfer blocks, improve block screening efficiency and retain potential strategic reserve areas.

[0109] Example 2 like Figure 2 As shown, this invention proposes a system for selecting non-oil and gas mineral exploration rights blocks based on geological data from a mineral exploration model. This system is implemented through the following steps: S1. Based on the results of geological reports, various mineral exploration prediction models are mined, extracted and standardized to form a mineral exploration model library. S2. Integrate and prepare geological text data, geological spatial data, and geological map data, and carry out indexing and annotation work on geological report texts and geological maps for mineral exploration prediction models; S3. Construct query matching conditions based on the mineral exploration model, quantify and conditionalize important mineral exploration indicators, and construct analogous matching conditions. S4. Matching conditions: Perform analogy matching in geological text data, geological spatial data, and geological map data, output location information, and select blocks with good mineralization geological background conditions.

[0110] S5. Evaluate each block based on the geological and mineral information contained in the geological data within the transfer block, and use semi-automatic and automatic technologies to extract, mine, and reorganize various types of information to form block evaluation materials.

[0111] Based on the above technical solutions, the present invention may employ the following additional technical means to better or more specifically achieve the objectives of the present invention: Further, step S1 includes the following sub-steps: S11. Based on the full-text database of geological reports, keyword retrieval of the full-text database of geological reports is carried out using keywords such as "mineral exploration model", "mineral exploration prediction model", "metallogenic model", "metallogenic element", "mineral exploration element", "prediction element", and "mineral exploration mode". S12. Extract the above keyword results and aggregate them to form the original library of mineral exploration models; S13. Based on the original mineral exploration model library, conduct data cleaning, organization, and standardization to form a standardized mineral exploration model library. Further, step S2 includes the following sub-steps: S21. Based on the 1:50,000 regional geological data in the collection, carry out spatial data integration, sorting and splicing, and form a searchable data format after code translation; S22. Based on the full-text database of geological reports and geological raster map data, use data items such as tectonic location, rock type, and metallogenic age in the mineral exploration model to carry out indexing and annotation work on geological reports; Further, step S3 includes the following sub-steps: S31. Based on the standardized mineral exploration model library, extract important mineral exploration indicator information to form a mineral exploration indicator library; S32. Based on important mineral exploration indicators, construct XML format data query matching conditions; Further, step S4 includes the following sub-steps: S41. Based on the XML format data matching conditions, perform query matching in the results of S21 and retain the location coordinate information of the matching area; S42. Based on the XML format data matching conditions, perform query matching in the S22 results, retain the matching geological reports and map coordinate information, and supplement them into the S41 results to form a candidate block library. Further, step S5 includes the following sub-steps: S51. Evaluate blocks based on the candidate block library. Select one candidate block and, based on coordinate information and the geological data catalog, construct a block geological data package. S52. Based on the geological data data package of sub-step S51, excavate the geological data within the block, including traffic location information, previous geological work, mineral exploration information, etc. S53. Based on the results of sub-step S52, fill in the proposal for the transfer of blocks and the geological evaluation table of the transfer of non-oil and gas mineral exploration rights; and based on the results of sub-step S51, form a list of important geological data for the transfer blocks.

[0112] In summary, non-oil and gas mineral exploration rights transfer blocks refer to areas with non-oil and gas mineral potential where exploration rights can be established, forming the foundation for a thriving mining market. Natural resources authorities need to expand the sources of transfer blocks, rapidly evaluate the geological conditions of transfer blocks, and significantly increase the number of blocks available for transfer to meet the demands of the exploration market. Selected blocks are submitted to the competent authority for transfer, promoting the stability and development of the mining market. This technical method is also applicable to mining enterprises, allowing them to utilize stored geological data for block selection, saving on field labor costs.

[0113] Example 3 To implement the methods of the above embodiments, the present invention also provides a prospecting rights transfer block selection device 10 based on a prospecting model, such as... Figure 3 As shown, it includes: The model extraction and standardization module 100 is used to extract and standardize mineral exploration prediction models based on the full-text database of geological reports, forming a mineral exploration model library containing mineralization elements. The data integration and semantic indexing module 200 is used to integrate geological text data, spatial data and map data, and to semantically index and annotate geological data using the geotectonic location, rock type and metallogenic age elements in the mineral exploration model. The tag conversion and XML generation module 300 is used to convert key mineral exploration tags in the mineral exploration model library into quantitative matching conditions in XML format. The analogy matching and candidate library construction module 400 is used to perform analogy matching in the labeled geological data based on the quantitative matching conditions, extract the coordinate information of the matching area and construct a candidate block library. The material generation and list construction module 500 is used to automatically generate block evaluation materials and a list of important geological data based on the coordinate information in the candidate block library and the geological data in the collection.

[0114] Furthermore, the model extraction and standardization module is also used for: Use preset keywords to perform keyword searches in the full-text database of geological reports; Extract keyword search results and aggregate them to form a raw library of mineral exploration models; Data cleaning, organization, and standardization were carried out on the original mineral exploration model library to form a standardized mineral exploration model library.

[0115] Furthermore, the data integration and semantic indexing module is also used for: Based on the 1:50,000 regional geological data in the collection, spatial data integration, sorting and splicing were carried out, and the data was converted into a searchable and retrieval format after code translation; Based on the full-text database of geological reports and geological raster map data, the geological reports are indexed and annotated using data items such as tectonic location, rock type, and metallogenic age in the mineral exploration model.

[0116] Furthermore, the markup conversion and XML generation module is also used for: Based on a standardized mineral exploration model library, important mineral exploration indicator information is extracted to form a mineral exploration indicator library; Based on important mineral exploration indicators, XML format data query matching conditions are constructed.

[0117] The prospecting rights transfer block selection device based on the prospecting model in this invention further optimizes the block classification management and transfer decision-making process by distinguishing between strategic and developmental selection areas and performing differentiated processing, thereby improving the scientific nature of strategic resource reserve planning and the pertinence and efficiency of prospecting rights transfer work.

[0118] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0119] In the description of this specification, the references to "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0120] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.< / mineralizationepoch>

Claims

1. A method for selecting the optimal exploration rights block based on a mineral exploration model, characterized in that, include: Based on the full-text database of geological reports, mineral exploration prediction models were extracted and standardized to form a mineral exploration model library containing mineralization elements. Integrate geological text data, spatial data, and map data, and use the geotectonic location, rock type, and metallogenic age elements in the mineral exploration model to perform semantic indexing and annotation on geological data; Convert key mineral exploration indicators in the mineral exploration model library into quantitative matching conditions in XML format; Based on quantitative matching conditions, analogical matching is performed on the labeled geological data to extract the coordinate information of the matching area and construct a candidate block library. Based on the coordinate information in the candidate block database, and combined with the geological data in the collection, the block evaluation materials and a list of important geological data are automatically generated.

2. The method as described in claim 1, characterized in that, The mineral exploration prediction model extracted and standardized from the full-text database of geological reports, forming a mineral exploration model library containing metallogenic elements, also includes: Use preset keywords to perform keyword searches in the full-text database of geological reports; Extract keyword search results and aggregate them to form a raw library of mineral exploration models; Data cleaning, organization, and standardization were carried out on the original mineral exploration model library to form a standardized mineral exploration model library.

3. The method as described in claim 1, characterized in that, The integrated geological text data, spatial data, and map data, along with the semantic indexing and annotation of geological data using tectonic location, rock type, and metallogenic epoch elements in the mineral exploration model, also includes: Based on the 1:50,000 regional geological data in the collection, spatial data integration, sorting and splicing were carried out, and the data was converted into a searchable and retrieval format after code translation; Based on the full-text database of geological reports and geological raster map data, the geological reports are indexed and annotated using data items such as tectonic location, rock type, and metallogenic age in the mineral exploration model.

4. The method as described in claim 1, characterized in that, The process of converting key mineral exploration indicators in the mineral exploration model library into quantitative matching conditions in XML format also includes: Based on a standardized mineral exploration model library, important mineral exploration indicator information is extracted to form a mineral exploration indicator library; Based on important mineral exploration indicators, XML format data query matching conditions are constructed.

5. The method as described in claim 1, characterized in that, The step of performing analogical matching on the labeled geological data based on XML matching conditions, extracting the coordinate information of the matching area, and constructing a candidate block library also includes: Based on XML format data matching conditions, query matching is carried out in the integrated and prepared spatial data, and the location coordinate information of the matching area is retained; Based on XML format data matching conditions, query and matching work is carried out in the geological reports and map data after indexing and annotation, the matching coordinate information is retained and supplemented to form a candidate block library.

6. The method as described in claim 1, characterized in that, The method further includes: Based on the evaluation results in the candidate block library, strategic selection areas are distinguished from development selection areas. Strategic selection areas are marked and archived separately, while exploration rights transfer proposals are generated for development selection areas.

7. A device for selecting exploration rights transfer blocks based on a mineral exploration model, characterized in that, include: The model extraction and standardization module is used to extract and standardize mineral exploration prediction models based on the full-text database of geological reports, forming a mineral exploration model library containing mineralization elements. The data integration and semantic indexing module is used to integrate geological text data, spatial data and map data, and to semantically index and annotate geological data using the geotectonic location, rock type and metallogenic age elements in the mineral exploration model. The token conversion and XML generation module is used to convert key mineral exploration tokens in the mineral exploration model library into quantitative matching conditions in XML format. The analogy matching and candidate library construction module is used to perform analogy matching on labeled geological data based on quantized matching conditions, extract coordinate information of matching areas and construct a candidate block library. The material generation and list construction module is used to automatically generate block evaluation materials and a list of important geological data based on the coordinate information in the candidate block library and the geological data in the collection.

8. The apparatus as claimed in claim 7, characterized in that, The model extraction and standardization module is also used for: Use preset keywords to perform keyword searches in the full-text database of geological reports; Extract keyword search results and aggregate them to form a raw library of mineral exploration models; Data cleaning, organization, and standardization were carried out on the original mineral exploration model library to form a standardized mineral exploration model library.

9. The apparatus as claimed in claim 7, characterized in that, The data integration and semantic indexing module is also used for: Based on the 1:50,000 regional geological data in the collection, spatial data integration, sorting and splicing were carried out, and the data was converted into a searchable and retrieval format after code translation; Based on the full-text database of geological reports and geological raster map data, the geological reports are indexed and annotated using data items such as tectonic location, rock type, and metallogenic age in the mineral exploration model.

10. The apparatus as claimed in claim 7, characterized in that, The flag conversion and XML generation module is also used for: Based on a standardized mineral exploration model library, important mineral exploration indicator information is extracted to form a mineral exploration indicator library; Based on important mineral exploration indicators, XML format data query matching conditions are constructed.

Images